Recent Posts

Pages: 1 ... 8 9 [10]
Wired - Science / How to Close the Gender Health Gap
« Last post by feeds on May 24, 2023, 06:40:02 AM »
How to Close the Gender Health Gap

Women’s health care and outcomes have long come a poor second to those of men. But new initiatives and a wave of healthtech innovators may finally rebalance this.
Source: How to Close the Gender Health Gap
Virgin Orbit: Branson’s rocket dream ends after mission failure

The British billionaire's bankrupt satellite launch firm had been looking to boost its finances.
Source: Virgin Orbit: Branson’s rocket dream ends after mission failure
MIT Research / A better way to match 3D volumes
« Last post by feeds on May 24, 2023, 06:40:00 AM »
A better way to match 3D volumes

In computer graphics and computer-aided design (CAD), 3D objects are often represented by the contours of their outer surfaces. Computers store these shapes as “thin shells,” which model the contours of the skin of an animated character but not the flesh underneath.

This modeling decision makes it efficient to store and manipulate 3D shapes, but it can lead to unexpected artifacts. An animated character’s hand, for example, might crumple when bending its fingers — a motion that resembles how an empty rubber glove deforms rather than the motion of a hand filled with bones, tendons, and muscle. These differences are particularly problematic when developing mapping algorithms, which automatically find relationships between different shapes.

To address these shortcomings, researchers at MIT have developed an approach that aligns 3D shapes by mapping volumes to volumes, rather than surfaces to surfaces. Their technique represents shapes as tetrahedral meshes that include the mass inside a 3D object. Their algorithm determines how to move and stretch the corners of tetrahedra in a source shape so it aligns with a target shape.

Because it incorporates volumetric information, the researchers’ technique is better able to model fine parts of an object, avoiding the twisting and inversion typical of surface-based mapping.

“Switching from surfaces to volumes stretches the rubber glove over the whole hand. Our method brings geometric mapping closer to physical reality,” says Mazdak Abulnaga, an electrical engineering and computer science (EECS) graduate student who is lead author of the paper on this mapping technique.

The approach Abulnaga and his collaborators developed was able to align shapes more effectively than baseline methods, leading to high-quality shape maps with less distortion than competing alternatives. Their algorithm was especially well-suited for challenging mapping problems where the input shapes are geometrically distinct, such as mapping a smooth rabbit to LEGO-style rabbit made of cubes.

The technique could be useful in a number of graphics applications. For instance, it could be used to transfer the motions of a previously animated 3D character onto a new 3D model or scan. The same algorithm can transfer textures, annotations, and physical properties from one 3D shape to another, with applications not just in visual computing but also for computational manufacturing and engineering.

Joining Abulnaga on the paper are Oded Stein, a former MIT postdoc who is now on the faculty at the University of Southern California; Polina Golland, a Sunlin and Priscilla Chou Professor of EECS, a principal investigator in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), and the leader of the Medical Vision Group; and Justin Solomon, an associate professor of EECS and the leader of the CSAIL Geometric Data Processing Group. The research will be presented at the ACM SIGGRAPH conference.

Shaping an algorithm

Abulnaga began this project by extending surface-based algorithms so they could map shapes volumetrically, but each attempt failed or produced implausible maps. The team quickly realized that new mathematics and algorithms were needed to tackle volume mapping.

Most mapping algorithms work by trying to minimize an “energy,” which quantifies how much a shape deforms when it is displaced, stretched, squashed, and sheared into another shape. These energies are often borrowed from physics, which uses similar equations to model the motion of elastic materials like gelatin.

Even when Abulnaga improved the energy in his mapping algorithm to better model volume physics, the method didn’t produce useful matchings. His team realized one reason for this failure is that many physical energies — and most mapping algorithms — lack symmetry.

In the new work, a symmetric method doesn’t care which order the shapes come in as input; there is no distinction between a “source” and “target” for the map. For example, mapping a horse onto a giraffe should produce the same matchings as mapping a giraffe onto a horse. But for many mapping algorithms, choosing the wrong shape to be the source or target leads to worse results. This effect is even more pronounced in the volumetric case.

Abulnaga documented how most mapping algorithms don’t use symmetric energies.

“If you choose the right energy for your algorithm, it can give you maps that are more realizable,” Abulnaga explains.

The typical energies used in shape alignment are only designed to map in one direction. If a researcher tries to apply them bidirectionally to create a symmetric map, the energies no longer behave as expected. These energies also behave differently when applied to surfaces and volumes.

Based on these findings, Abulnaga and his collaborators created a mathematical framework that researchers can use to see how different energies will behave and to determine which they should choose to create a symmetric map between two objects. Using this framework, they built a mapping algorithm that combines the energy functions for two objects in a way that guarantees symmetry throughout.

A user feeds the algorithm two shapes that are represented as tetrahedral meshes. Then the algorithm computes two bidirectional maps, from one shape to the other and back. These maps show where each corner of each tetrahedron should move to match the shapes.

“The energy is the cornerstone of this mapping process. The model tries to align the two shapes, and the energies prevent it from making unexpected alignments,” he says.

Achieving accurate alignments

When the researchers tested their approach, it created maps that better aligned shape pairs and which were higher quality and less distorted than other approaches that work on volumes. They also showed that using volume information can yield more accurate maps even when one is only concerned with the map of the outer surface.

However, there were some cases where their method fell short. For instance, the algorithm struggles when the shape alignment requires a great deal of volume changes, such as mapping a shape with a filled interior to one with a cavity inside.

In addition to addressing that limitation, the researchers want to continue optimizing the algorithm to reduce the amount of time it takes. The researchers are also working on extending this method to medical applications, bringing in MRI signals in addition to shape. This can help bridge the mapping approaches used in medical computer vision and computer graphics.

“A theoretical analysis of symmetry drives the development of this algorithm and shows that symmetric shape comparison methods tend to have better performance in comparing and aligning objects,” says Joel Haas, distinguished professor in the Department of Mathematics at the University of California at Davis, who was not involved with this work. “Alignments based exclusively on surface data can lead to collapsed volumes, as occasionally happened to Wile E. Coyote in the ‘Road Runner’ cartoons. A range of experiments shows that the new algorithm has remarkable success in maintaining interior consistency while aligning a pair of 3D objects. It gives a good correspondence throughout the interior as well as on the boundary.”

This research is funded, in part, by the National Institutes of Health, Wistron Corporation, the U.S. Army Research Office, the Air Force Office of Scientific Research, the National Science Foundation, the CSAIL Systems that Learn Program, the MIT-IBM Watson AI Lab, the Toyota-CSAIL Joint Research Center, Adobe Systems, the Swiss National Science Foundation, the Natural Sciences and Engineering Research Council of Canada, and a Mathworks Fellowship.

Source: A better way to match 3D volumes
MIT Research / Tiny diamond rotor could improve protein studies
« Last post by feeds on May 24, 2023, 06:40:00 AM »
Tiny diamond rotor could improve protein studies

Many of the biological materials that researchers are most interested in studying, including those associated with major diseases, don’t lend themselves to the conventional methods that researchers typically use to probe a material’s structure and chemistry.

One technique, called magic-angle spinning nuclear magnetic resonance, or MAS-NMR, has proven highly successful as a way of determining the properties of complex molecules such as some proteins. But the resolution achievable with such systems depends on the spinning frequency of tiny rotors, and these systems have bumped up against limits imposed by the rotor materials.

Most such devices used today rely on rotors made of yttria-stabilized zirconia, which are as thin as a pin. Such rotors fall apart if spun much faster than a few million revolutions per minute, limiting the materials that can be studied with such systems. But now, researchers at MIT have developed a method for making these tiny, precise rotors out of pure diamond crystal, whose much greater strength could allow it to spin at far higher frequencies. The advance opens the door to studying a wide variety of important molecules, including those found in the amyloid plaques associated with Alzheimer’s disease.

The new method is described in the Journal of Magnetic Resonance, in a paper by MIT graduate students Natalie Golota, Zachary Fredin, Daniel Banks, and David Preiss; professors Robert Griffin, Neil Gershenfeld, and Keith Nelson; and seven others at MIT.

The MAS-NMR technique, Gershenfeld says, “is the tool of choice for [analyzing] complex biological proteins in biologically meaningful environments.” For example, a sample could be analyzed in a liquid environment as opposed to being dried out or crystallized or coated for examination. “Only [solid-state] NMR does it in the ambient chemical environment,” he says.

The basic method has existed for decades, Griffin explains, and involves placing a tiny cylinder filled with the material to be studied into a magnetic field where it can be suspended and spun up to high frequencies using jets of gas, usually nitrogen, and then zapped with radio-frequency pulses to determine key properties of the material. The term “magic angle” refers to the fact that if the cylinder containing the sample spins at one precise angle (54.74 degrees) relative to the applied magnetic field, various sources of broadening of the spectral lines are attenuated and a much higher-resolution spectrum is possible.

Animated monochrome clip of inside of a spinning diamond as hole in center glows becomes increasingly round. Red lines resembling a shooting scope overlay the animation.

But the resolution of these spectra is directly limited by how fast the tiny cylinders, or rotors, can spin before they shatter. Over the years, early versions were made of various plastics, then later ceramic materials were used, and finally zirconium, “which is the material of choice that most rotors are made of these days,” Griffin says.

Such MAS-NMR systems are widely used in biochemical research as a tool for studying the molecular structure, down to the level of individual atoms, of materials including proteins that are difficult or impossible to probe using other standard lab methods. These include not only amyloid fibrils, but membrane proteins and some viral assemblies. But some of the most pressing challenges in both biomedical and materials science lie just beyond reach of the resolution of today’s MAS-NMR systems.

“As we progressed to spinning frequencies above 100 kilohertz,” equivalent to 6 million revolutions per minute, Griffin says, “these rotors have become very problematic. They fail about 50 percent of the time — and you lose a sample, and it destroys the NMR coil.” The team decided to tackle the problem, which many said at the time was impossible, of making the rotors out of single crystal diamond.

Even the company making the laser system they used thought it couldn’t be done, and it took years of work by an interdisciplinary team, involving students and researchers at both MIT’s Center for Bits and Atoms and the Department of Chemistry, to solve that fabrication problem. (The collaboration grew out of  Griffin and Gershenfeld serving on MIT’s Killian Award Committee). They developed a kind of laser-based lathe system that rapidly spins a piece of diamond while zapping it with the laser, essentially vaporizing its outer layers until a perfectly smooth cylinder remains, just 0.7 millimeters across (about 1/36 inch). Then, the same laser is used to drill a perfectly centered hole through the middle of the cylinder, leaving a sort of drinking-straw shape.

“It’s not obvious it would work,” Gershenfeld says, “but the laser turns the diamond into graphite and drives the carbon off, and you can incrementally do that to drill deep into the diamond.”

The diamond emerges from the machining process with a black coating of pure graphite, but the MIT researchers found that this could be eliminated by heating the rotor overnight at about 600 degrees Celsius (about 1,100 degrees Fahrenheit.) The result is a rotor that can already spin at 6 million revolutions per minute, the speed of the best zirconia rotors, and has other advantageous characteristics as well, including extremely high thermal conductivity and radio-frequency transparency.

Fredin points out that all the parts needed to make this high-precision machining system “were all designed and fabricated right here” in a basement lab in the Center for Bits and Atoms. “To be able to physically design and make everything and iterate it many times a day in-house was a crucial aspect of this project, as opposed to having to send things out to outside machine shops.”

Achieving much higher spinning frequencies should now be possible with these new rotors, the researchers say, but will require the development of new bearings and new systems based on helium rather than nitrogen to drive the rotation, in order to achieve the increased speeds and the corresponding leap in resolution. “It was never worth it to develop these helium-compatible bearings for these small rotors until this technology was proven out, when the rotors previously used would not be able to withstand the spinning speeds,” which could end up going as high as 20 million revolutions per minute, Golota says.

Such high rotation rates are almost unheard of outside the NMR field. Preiss says that as a mechanical engineer, “it’s rare that you’d encounter something spinning above tens of thousands of rpm.” When he first heard the 6 million rpm figure for these devices, he says, “I kind of thought it was a joke.”

Because of these high speeds, Gershenfeld says, instabilities can easily arise from any imperfection: “If there’s even a slight asymmetry in the structure, at these frequencies, you’re doomed.”

Golota says that in her experiments using current zirconia rotors, “when the rotors fail, they explode, and you essentially just recover dust. But when the diamond rotors fail, we were able to recover them intact. So, you’re saving the sample as well, which can be an invaluable resource to the user.”

They have already used the new diamond rotor to produce the carbon-13 and nitrogen-15 spectra of a small peptide, clearly demonstrating the capabilities of the new diamond rotor material, which Griffin says is the first new material for such rotors to be developed in the last three decades. “We’ve used spectra like these extensively,” he says, “to determine the structure of amyloid-beta 1-42, which is a toxic species in Alzheimer’s disease.” Samples of such material are hard to get and usually obtainable only in tiny quantities, he says. “We now have a small rotor that’s going to be hopefully very reliable where you can put in two or three milligrams of material and get spectral data like these,” he says, pointing to the sample data they obtained. “It’s really exciting and it’s going to open up a lot of new areas of research.”

This work “is truly remarkable,” says David Doty, president of Doty Scientific, a maker of NMR systems, who was not involved in this work. “It would have been very hard to find anyone outside this group who would have thought it possible to laser machine diamond rotors with the precision needed for fast-MAS, prior to actually seeing it work,” he says.

Doty adds, “What they have demonstrated thus far … is nothing short of amazing.  If the additional needed progress can be made, hundreds of NMR researchers will want these to help them get better data for the projects they are working on, from improving our understanding of some diseases and developing better drugs to developing advanced battery materials.”

“This new technology has the potential to be a game-changer in the way we will carry out solid-state NMR experiments in the future, opening unprecedented experimental opportunities in terms of resolution and sensitivity,” says Anne Lesage, adjunct director of the institute of analytical sciences at the Ecole Normale Superieure in Lyon, France, who also was not associated with this work.

The research team also included Salima Bahri, Daniel Banks, Prashant Patil, William Langford, Camron Blackburn, Erik Strand, Brian Michael, and Blake Dastrup, all at MIT. The work was supported by the U.S. National Institutes of Health, the CBA Consortia fund, the U.S. Department of Energy, and the U.S. National Science Foundation.

Source: Tiny diamond rotor could improve protein studies
Exploring new methods for increasing safety and reliability of autonomous vehicles

When we think of getting on the road in our cars, our first thoughts may not be that fellow drivers are particularly safe or careful — but human drivers are more reliable than one may expect. For each fatal car crash in the United States, motor vehicles log a whopping hundred million miles on the road.

Human reliability also plays a role in how autonomous vehicles are integrated in the traffic system, especially around safety considerations. Human drivers continue to surpass autonomous vehicles in their ability to make quick decisions and perceive complex environments: Autonomous vehicles are known to struggle with seemingly common tasks, such as taking on- or off-ramps, or turning left in the face of oncoming traffic. Despite these enormous challenges, embracing autonomous vehicles in the future could yield great benefits, like clearing congested highways; enhancing freedom and mobility for non-drivers; and boosting driving efficiency, an important piece in fighting climate change.

MIT engineer Cathy Wu envisions ways that autonomous vehicles could be deployed with their current shortcomings, without experiencing a dip in safety. “I started thinking more about the bottlenecks. It’s very clear that the main barrier to deployment of autonomous vehicles is safety and reliability,” Wu says.

One path forward may be to introduce a hybrid system, in which autonomous vehicles handle easier scenarios on their own, like cruising on the highway, while transferring more complicated maneuvers to remote human operators. Wu, who is a member of the Laboratory for Information and Decision Systems (LIDS), a Gilbert W. Winslow Assistant Professor of Civil and Environmental Engineering (CEE) and a member of the MIT Institute for Data, Systems, and Society (IDSS), likens this approach to air traffic controllers on the ground directing commercial aircraft.

In a paper published April 12 in IEEE Transactions on Robotics, Wu and co-authors Cameron Hickert and Sirui Li (both graduate students at LIDS) introduced a framework for how remote human supervision could be scaled to make a hybrid system efficient without compromising passenger safety. They noted that if autonomous vehicles were able to coordinate with each other on the road, they could reduce the number of moments in which humans needed to intervene.

Humans and cars: finding a balance that’s just right

For the project, Wu, Hickert, and Li sought to tackle a maneuver that autonomous vehicles often struggle to complete. They decided to focus on merging, specifically when vehicles use an on-ramp to enter a highway. In real life, merging cars must accelerate or slow down in order to avoid crashing into cars already on the road. In this scenario, if an autonomous vehicle was about to merge into traffic, remote human supervisors could momentarily take control of the vehicle to ensure a safe merge. In order to evaluate the efficiency of such a system, particularly while guaranteeing safety, the team specified the maximum amount of time each human supervisor would be expected to spend on a single merge. They were interested in understanding whether a small number of remote human supervisors could successfully manage a larger group of autonomous vehicles, and the extent to which this human-to-car ratio could be improved while still safely covering every merge.

With more autonomous vehicles in use, one might assume a need for more remote supervisors. But in scenarios where autonomous vehicles coordinated with each other, the team found that cars could significantly reduce the number of times humans needed to step in. For example, a coordinating autonomous vehicle already on a highway could adjust its speed to make room for a merging car, eliminating a risky merging situation altogether.

The team substantiated the potential to safely scale remote supervision in two theorems. First, using a mathematical framework known as queuing theory, the researchers formulated an expression to capture the probability of a given number of supervisors failing to handle all merges pooled together from multiple cars. This way, the researchers were able to assess how many remote supervisors would be needed in order to cover every potential merge conflict, depending on the number of autonomous vehicles in use. The researchers derived a second theorem to quantify the influence of cooperative autonomous vehicles on surrounding traffic for boosting reliability, to assist cars attempting to merge.

When the team modeled a scenario in which 30 percent of cars on the road were cooperative autonomous vehicles, they estimated that a ratio of one human supervisor to every 47 autonomous vehicles could cover 99.9999 percent of merging cases. But this level of coverage drops below 99 percent, an unacceptable range, in scenarios where autonomous vehicles did not cooperate with each other.

“If vehicles were to coordinate and basically prevent the need for supervision, that’s actually the best way to improve reliability,” Wu says.

Cruising toward the future

The team decided to focus on merging not only because it’s a challenge for autonomous vehicles, but also because it’s a well-defined task associated with a less-daunting scenario: driving on the highway. About half of the total miles traveled in the United States occur on interstates and other freeways. Since highways allow higher speeds than city roads, Wu says, “If you can fully automate highway driving … you give people back about a third of their driving time.”

If it became feasible for autonomous vehicles to cruise unsupervised for most highway driving, the challenge of safely navigating complex or unexpected moments would remain. For instance, “you [would] need to be able to handle the start and end of the highway driving,” Wu says. You would also need to be able to manage times when passengers zone out or fall asleep, making them unable to quickly take over controls should it be needed. But if remote human supervisors could guide autonomous vehicles at key moments, passengers may never have to touch the wheel. Besides merging, other challenging situations on the highway include changing lanes and overtaking slower cars on the road.

Although remote supervision and coordinated autonomous vehicles are hypotheticals for high-speed operations, and not currently in use, Wu hopes that thinking about these topics can encourage growth in the field.

“This gives us some more confidence that the autonomous driving experience can happen,” Wu says. “I think we need to be more creative about what we mean by ‘autonomous vehicles.’ We want to give people back their time — safely. We want the benefits, we don’t strictly want something that drives autonomously.”

Source: Exploring new methods for increasing safety and reliability of autonomous vehicles
Wired - Science / How NASA Plans to Melt the Moon—and Build on Mars
« Last post by feeds on May 23, 2023, 12:28:33 PM »
How NASA Plans to Melt the Moon—and Build on Mars

Scientists are testing ways to construct buildings on Mars and the moon without hauling materials from Earth. One possible solution: 3D printed melted regolith.
Source: How NASA Plans to Melt the Moon—and Build on Mars
Wired - Science / New York City Is Sinking. It’s Far From Alone
« Last post by feeds on May 23, 2023, 12:28:33 PM »
New York City Is Sinking. It’s Far From Alone

The Big Apple is subsiding under its own weight. But other coastal cities are also dramatically descending, just as seas are rising.
Source: New York City Is Sinking. It’s Far From Alone
Bird flu: Brazil declares animal health emergency after several cases found

The country is the world's largest exporter of chicken meat, and wants to stop the virus spreading.
Source: Bird flu: Brazil declares animal health emergency after several cases found
Biodiversity: Almost half of animals in decline, research shows

A study led by Queen's University Belfast finds 48% of species are undergoing population declines.
Source: Biodiversity: Almost half of animals in decline, research shows
MIT Research / Researchers use AI to identify similar materials in images
« Last post by feeds on May 23, 2023, 12:28:32 PM »
Researchers use AI to identify similar materials in images

A robot manipulating objects while, say, working in a kitchen, will benefit from understanding which items are composed of the same materials. With this knowledge, the robot would know to exert a similar amount of force whether it picks up a small pat of butter from a shadowy corner of the counter or an entire stick from inside the brightly lit fridge.

Identifying objects in a scene that are composed of the same material, known as material selection, is an especially challenging problem for machines because a material’s appearance can vary drastically based on the shape of the object or lighting conditions.

Scientists at MIT and Adobe Research have taken a step toward solving this challenge. They developed a technique that can identify all pixels in an image representing a given material, which is shown in a pixel selected by the user.

The method is accurate even when objects have varying shapes and sizes, and the machine-learning model they developed isn’t tricked by shadows or lighting conditions that can make the same material appear different.

Although they trained their model using only “synthetic” data, which are created by a computer that modifies 3D scenes to produce many varying images, the system works effectively on real indoor and outdoor scenes it has never seen before. The approach can also be used for videos; once the user identifies a pixel in the first frame, the model can identify objects made from the same material throughout the rest of the video.

Four images shown horizontally of person walking with luggage. First, image still shows red dot on yellow pants material. Second and third images are animations, but the third image shows pink pants. Fourth, monochrome version animation is shown, with luggage and shoes barely visible in black background.

In addition to applications in scene understanding for robotics, this method could be used for image editing or incorporated into computational systems that deduce the parameters of materials in images. It could also be utilized for material-based web recommendation systems. (Perhaps a shopper is searching for clothing made from a particular type of fabric, for example.)

“Knowing what material you are interacting with is often quite important. Although two objects may look similar, they can have different material properties. Our method can facilitate the selection of all the other pixels in an image that are made from the same material,” says Prafull Sharma, an electrical engineering and computer science graduate student and lead author of a paper on this technique.

Sharma’s co-authors include Julien Philip and Michael Gharbi, research scientists at Adobe Research; and senior authors William T. Freeman, the Thomas and Gerd Perkins Professor of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL); Frédo Durand, a professor of electrical engineering and computer science and a member of CSAIL; and Valentin Deschaintre, a research scientist at Adobe Research. The research will be presented at the SIGGRAPH 2023 conference.

A new approach

Existing methods for material selection struggle to accurately identify all pixels representing the same material. For instance, some methods focus on entire objects, but one object can be composed of multiple materials, like a chair with wooden arms and a leather seat. Other methods may utilize a predetermined set of materials, but these often have broad labels like “wood,” despite the fact that there are thousands of varieties of wood.

Instead, Sharma and his collaborators developed a machine-learning approach that dynamically evaluates all pixels in an image to determine the material similarities between a pixel the user selects and all other regions of the image. If an image contains a table and two chairs, and the chair legs and tabletop are made of the same type of wood, their model could accurately identify those similar regions.

Before the researchers could develop an AI method to learn how to select similar materials, they had to overcome a few hurdles. First, no existing dataset contained materials that were labeled finely enough to train their machine-learning model. The researchers rendered their own synthetic dataset of indoor scenes, which included 50,000 images and more than 16,000 materials randomly applied to each object.

“We wanted a dataset where each individual type of material is marked independently,” Sharma says.

Synthetic dataset in hand, they trained a machine-learning model for the task of identifying similar materials in real images — but it failed. The researchers realized distribution shift was to blame. This occurs when a model is trained on synthetic data, but it fails when tested on real-world data that can be very different from the training set.

To solve this problem, they built their model on top of a pretrained computer vision model, which has seen millions of real images. They utilized the prior knowledge of that model by leveraging the visual features it had already learned.

“In machine learning, when you are using a neural network, usually it is learning the representation and the process of solving the task together. We have disentangled this. The pretrained model gives us the representation, then our neural network just focuses on solving the task,” he says.

Solving for similarity

The researchers’ model transforms the generic, pretrained visual features into material-specific features, and it does this in a way that is robust to object shapes or varied lighting conditions.

Four images shown horizontally row of matches. First, image still shows red dot on match tip in the center. Second and third images are animations of flame on opposite ends as they reach the center, but the third image shows the center matches blaze a bright red. Fourth, monochrome version animation is shown, with the flame barely visible in black background.

The model can then compute a material similarity score for every pixel in the image. When a user clicks a pixel, the model figures out how close in appearance every other pixel is to the query. It produces a map where each pixel is ranked on a scale from 0 to 1 for similarity.

“The user just clicks one pixel and then the model will automatically select all regions that have the same material,” he says.

Since the model is outputting a similarity score for each pixel, the user can fine-tune the results by setting a threshold, such as 90 percent similarity, and receive a map of the image with those regions highlighted. The method also works for cross-image selection — the user can select a pixel in one image and find the same material in a separate image.

During experiments, the researchers found that their model could predict regions of an image that contained the same material more accurately than other methods. When they measured how well the prediction compared to ground truth, meaning the actual areas of the image that are comprised of the same material, their model matched up with about 92 percent accuracy.

In the future, they want to enhance the model so it can better capture fine details of the objects in an image, which would boost the accuracy of their approach.

“Rich materials contribute to the functionality and beauty of the world we live in. But computer vision algorithms typically overlook materials, focusing heavily on objects instead. This paper makes an important contribution in recognizing materials in images and video across a broad range of challenging conditions,” says Kavita Bala, Dean of the Cornell Bowers College of Computing and Information Science and Professor of Computer Science, who was not involved with this work. “This technology can be very useful to end consumers and designers alike. For example, a home owner can envision how expensive choices like reupholstering a couch, or changing the carpeting in a room, might appear, and can be more confident in their design choices based on these visualizations.”

Source: Researchers use AI to identify similar materials in images
Pages: 1 ... 8 9 [10]


NEUZ.COM ™ All Rights Reserved.