Close Menu
Ztoog
    What's Hot
    Technology

    YouTube TV’s Multiview feature could soon roll out to iPhones and iPads

    Science

    How can we prove the world is really quantum mechanical?

    Science

    This Is the Quietest Sound in the Universe

    Important Pages:
    • About Us
    • Contact us
    • Privacy Policy
    • Terms & Conditions
    Facebook X (Twitter) Instagram Pinterest
    Facebook X (Twitter) Instagram Pinterest
    Ztoog
    • Home
    • The Future

      Any wall can be turned into a camera to see around corners

      JD Vance and President Trump’s Sons Hype Bitcoin at Las Vegas Conference

      AI may already be shrinking entry-level jobs in tech, new research suggests

      Today’s NYT Strands Hints, Answer and Help for May 26 #449

      LiberNovo Omni: The World’s First Dynamic Ergonomic Chair

    • Technology

      A Replit employee details a critical security flaw in web apps created using AI-powered app builder Lovable that exposes API keys and personal info of app users (Reed Albergotti/Semafor)

      Gemini in Google Drive can now help you skip watching that painfully long Zoom meeting

      Apple iPhone exports from China to the US fall 76% as India output surges

      Today’s NYT Wordle Hints, Answer and Help for May 26, #1437

      5 Skills Kids (and Adults) Need in an AI World – O’Reilly

    • Gadgets

      8 Best Vegan Meal Delivery Services and Kits (2025), Tested and Reviewed

      Google Home is getting deeper Gemini integration and a new widget

      Google Announces AI Ultra Subscription Plan With Premium Features

      Google shows off Android XR-based glasses, announces Warby Parker team-up

      The market’s down, but this OpenAI for the stock market can help you trade up

    • Mobile

      Microsoft is done being subtle – this new tool screams “upgrade now”

      Wallpaper Wednesday: Android wallpapers 2025-05-28

      Google can make smart glasses accessible with Warby Parker, Gentle Monster deals

      vivo T4 Ultra specs leak

      Forget screens: more details emerge on the mysterious Jony Ive + OpenAI device

    • Science

      Analysts Say Trump Trade Wars Would Harm the Entire US Energy Sector, From Oil to Solar

      Do we have free will? Quantum experiments may soon reveal the answer

      Was Planet Nine exiled from the solar system as a baby?

      How farmers can help rescue water-loving birds

      A trip to the farm where loofahs grow on vines

    • AI

      Rationale engineering generates a compact new tool for gene therapy | Ztoog

      The AI Hype Index: College students are hooked on ChatGPT

      Learning how to predict rare kinds of failures | Ztoog

      Anthropic’s new hybrid AI model can work on tasks autonomously for hours at a time

      AI learns how vision and sound are connected, without human intervention | Ztoog

    • Crypto

      GameStop bought $500 million of bitcoin

      CoinW Teams Up with Superteam Europe to Conclude Solana Hackathon and Accelerate Web3 Innovation in Europe

      Ethereum Net Flows Turn Negative As Bulls Push For $3,500

      Bitcoin’s Power Compared To Nuclear Reactor By Brazilian Business Leader

      Senate advances GENIUS Act after cloture vote passes

    Ztoog
    Home » Researchers use AI to identify similar materials in images | Ztoog
    AI

    Researchers use AI to identify similar materials in images | Ztoog

    Facebook Twitter Pinterest WhatsApp
    Researchers use AI to identify similar materials in images | Ztoog
    Share
    Facebook Twitter LinkedIn Pinterest WhatsApp

    A robotic manipulating objects whereas, say, working in a kitchen, will profit from understanding which objects are composed of the identical materials. With this data, the robotic would know to exert a similar quantity of power whether or not it picks up a small pat of butter from a shadowy nook of the counter or a whole stick from contained in the brightly lit fridge.

    Identifying objects in a scene which are composed of the identical materials, often known as materials choice, is an particularly difficult downside for machines as a result of a cloth’s look can fluctuate drastically based mostly on the form of the thing or lighting situations.

    Scientists at MIT and Adobe Research have taken a step towards fixing this problem. They developed a way that may identify all pixels in a picture representing a given materials, which is proven in a pixel chosen by the person.

    The methodology is correct even when objects have various styles and sizes, and the machine-learning mannequin they developed isn’t tricked by shadows or lighting situations that may make the identical materials seem completely different.

    Although they educated their mannequin utilizing solely “synthetic” information, that are created by a pc that modifies 3D scenes to produce many ranging images, the system works successfully on actual indoor and out of doors scenes it has by no means seen earlier than. The method may also be used for movies; as soon as the person identifies a pixel in the primary body, the mannequin can identify objects comprised of the identical materials all through the remainder of the video.

    The researchers’ approach may also be used to choose similar materials in a video. The person identifies a pixel in the primary body (crimson dot in the far-left picture on the yellow cloth) and the system mechanically identifies objects comprised of the identical materials all through the remainder of the video.

    Image: Courtesy of the researchers

    In addition to functions in scene understanding for robotics, this methodology could possibly be used for picture enhancing or included into computational techniques that deduce the parameters of materials in images. It may be utilized for material-based net suggestion techniques. (Perhaps a client is looking for clothes comprised of a specific kind of cloth, for instance.)

    “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 laptop science graduate pupil and lead writer of a paper on this method.

    Sharma’s co-authors embody Julien Philip and Michael Gharbi, analysis 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 laptop science and a member of CSAIL; and Valentin Deschaintre, a analysis scientist at Adobe Research. The analysis will probably be introduced on the SIGGRAPH 2023 convention.

    A brand new method

    Existing strategies for materials choice wrestle to precisely identify all pixels representing the identical materials. For occasion, some strategies give attention to total objects, however one object may be composed of a number of materials, like a chair with wood arms and a leather-based seat. Other strategies could make the most of a predetermined set of materials, however these usually have broad labels like “wood,” even if there are millions of kinds of wooden.

    Instead, Sharma and his collaborators developed a machine-learning method that dynamically evaluates all pixels in a picture to decide the fabric similarities between a pixel the person selects and all different areas of the picture. If a picture comprises a desk and two chairs, and the chair legs and tabletop are manufactured from the identical kind of wooden, their mannequin might precisely identify these similar areas.

    Before the researchers might develop an AI methodology to find out how to choose similar materials, that they had to overcome a number of hurdles. First, no present dataset contained materials that have been labeled finely sufficient to prepare their machine-learning mannequin. The researchers rendered their very own artificial dataset of indoor scenes, which included 50,000 images and greater than 16,000 materials randomly utilized to every object.

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

    Synthetic dataset in hand, they educated a machine-learning mannequin for the duty of figuring out similar materials in actual images — but it surely failed. The researchers realized distribution shift was to blame. This happens when a mannequin is educated on artificial information, but it surely fails when examined on real-world information that may be very completely different from the coaching set.

    To remedy this downside, they constructed their mannequin on prime of a pretrained laptop imaginative and prescient mannequin, which has seen hundreds of thousands of actual images. They utilized the prior data of that mannequin by leveraging the visible options it had already discovered.

    “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’ mannequin transforms the generic, pretrained visible options into material-specific options, and it does this in a manner that’s strong to object shapes or various lighting situations.

    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 system the researchers developed to identify similar materials is powerful to adjustments in lighting situations, as seen in this instance of match heads burning.

    Image: Courtesy of the researchers

    The mannequin can then compute a cloth similarity rating for each pixel in the picture. When a person clicks a pixel, the mannequin figures out how shut in look each different pixel is to the question. It produces a map the place every 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 mannequin is outputting a similarity rating for every pixel, the person can fine-tune the outcomes by setting a threshold, similar to 90 % similarity, and obtain a map of the picture with these areas highlighted. The methodology additionally works for cross-image choice — the person can choose a pixel in one picture and discover the identical materials in a separate picture.

    During experiments, the researchers discovered that their mannequin might predict areas of a picture that contained the identical materials extra precisely than different strategies. When they measured how properly the prediction in contrast to floor fact, which means the precise areas of the picture which are comprised of the identical materials, their mannequin matched up with about 92 % accuracy.

    In the longer term, they need to improve the mannequin so it may higher seize fantastic particulars of the objects in a picture, which might enhance the accuracy of their method.

    “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 concerned 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.”

    Share. Facebook Twitter Pinterest LinkedIn WhatsApp

    Related Posts

    AI

    Rationale engineering generates a compact new tool for gene therapy | Ztoog

    AI

    The AI Hype Index: College students are hooked on ChatGPT

    AI

    Learning how to predict rare kinds of failures | Ztoog

    AI

    Anthropic’s new hybrid AI model can work on tasks autonomously for hours at a time

    AI

    AI learns how vision and sound are connected, without human intervention | Ztoog

    AI

    How AI is introducing errors into courtrooms

    AI

    With AI, researchers predict the location of virtually any protein within a human cell | Ztoog

    AI

    Google DeepMind’s new AI agent cracks real-world problems better than humans can

    Leave A Reply Cancel Reply

    Follow Us
    • Facebook
    • Twitter
    • Pinterest
    • Instagram
    Top Posts
    The Future

    12 Tips To Maximize Productivity With Enterprise Mobility Management

    The fashionable workforce is extra cellular than ever earlier than. Employees anticipate the flexibleness to…

    Technology

    Meta Connect 2023: Everything announced so far

    Meta’s annual Connect convention began immediately, and this implies numerous new {hardware} and maybe a…

    Crypto

    Dispersion Capital launches $40M fund focused on decentralized infrastructure

    This deep into the crypto winter large enterprise fund debuts are few and much between,…

    The Future

    Remote Work Guide: How to Secure Your Home Network

    Globally, extra individuals are working from dwelling. If your community is ever breached, you need…

    Mobile

    Samsung signs a multi-year deal with Qualcomm to continue receiving Snapdragon chips

    Even although the Samsung Exynos 2400 Deca-core utility processor (AP) carried out strongly on benchmark…

    Our Picks
    AI

    This AI Paper Unveils How Multilingual Instruction-Tuning Boosts Cross-Lingual Understanding in Large Language Models

    Crypto

    Why Is Bitcoin Down Today?

    Gadgets

    Hands-on with Cherry MX2A switches: A lot less wobble, a little more confusion

    Categories
    • AI (1,493)
    • Crypto (1,753)
    • Gadgets (1,804)
    • Mobile (1,850)
    • Science (1,866)
    • Technology (1,802)
    • The Future (1,648)
    Most Popular
    AI

    Researchers from the University of Washington and NVIDIA Propose Humanoid Agents: An Artificial Intelligence Platform for Human-like Simulations of Generative Agents

    Gadgets

    OnePlus Nord CE 3 5G Review: A Solid Mid Ranger With Great Potential

    Crypto

    EU to Crack Down on Crypto Tax Evasion with Greater Surveillance: Impending Legislation

    Ztoog
    Facebook X (Twitter) Instagram Pinterest
    • Home
    • About Us
    • Contact us
    • Privacy Policy
    • Terms & Conditions
    © 2025 Ztoog.

    Type above and press Enter to search. Press Esc to cancel.