{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/differential-angular-imaging-for-material","title":"Differential Angular Imaging for Material Recognition","arxiv_id":"1612.02372","date":"2016-12-07","proceeding":"CVPR 2017 7","authors":["Jia Xue","Hang Zhang","Kristin Dana","Ko Nishino"],"abstract":"Material recognition for real-world outdoor surfaces has become increasingly\nimportant for computer vision to support its operation \"in the wild.\"\nComputational surface modeling that underlies material recognition has\ntransitioned from reflectance modeling using in-lab controlled radiometric\nmeasurements to image-based representations based on internet-mined images of\nmaterials captured in the scene. We propose to take a middle-ground approach\nfor material recognition that takes advantage of both rich radiometric cues and\nflexible image capture. We realize this by developing a framework for\ndifferential angular imaging, where small angular variations in image capture\nprovide an enhanced appearance representation and significant recognition\nimprovement. We build a large-scale material database, Ground Terrain in\nOutdoor Scenes (GTOS) database, geared towards real use for autonomous agents.\nThe database consists of over 30,000 images covering 40 classes of outdoor\nground terrain under varying weather and lighting conditions. We develop a\nnovel approach for material recognition called a Differential Angular Imaging\nNetwork (DAIN) to fully leverage this large dataset. With this novel network\narchitecture, we extract characteristics of materials encoded in the angular\nand spatial gradients of their appearance. Our results show that DAIN achieves\nrecognition performance that surpasses single view or coarsely quantized\nmultiview images. These results demonstrate the effectiveness of differential\nangular imaging as a means for flexible, in-place material recognition.","url_abs":"http://arxiv.org/abs/1612.02372v2","url_pdf":"http://arxiv.org/pdf/1612.02372v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"material-recognition","task_name":"Material Recognition"}],"methods":[],"datasets_introduced":[{"slug":"gtos","name":"GTOS","full_name":"Ground Terrain in Outdoor Scenes"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.02372","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}