{"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/learning-rich-features-from-rgb-d-images-for","title":"Learning Rich Features from RGB-D Images for Object Detection and Segmentation","arxiv_id":"1407.5736","date":"2014-07-22","proceeding":null,"authors":["Saurabh Gupta","Ross Girshick","Pablo Arbeláez","Jitendra Malik"],"abstract":"In this paper we study the problem of object detection for RGB-D images using\nsemantically rich image and depth features. We propose a new geocentric\nembedding for depth images that encodes height above ground and angle with\ngravity for each pixel in addition to the horizontal disparity. We demonstrate\nthat this geocentric embedding works better than using raw depth images for\nlearning feature representations with convolutional neural networks. Our final\nobject detection system achieves an average precision of 37.3%, which is a 56%\nrelative improvement over existing methods. We then focus on the task of\ninstance segmentation where we label pixels belonging to object instances found\nby our detector. For this task, we propose a decision forest approach that\nclassifies pixels in the detection window as foreground or background using a\nfamily of unary and binary tests that query shape and geocentric pose features.\nFinally, we use the output from our object detectors in an existing superpixel\nclassification framework for semantic scene segmentation and achieve a 24%\nrelative improvement over current state-of-the-art for the object categories\nthat we study. We believe advances such as those represented in this paper will\nfacilitate the use of perception in fields like robotics.","url_abs":"http://arxiv.org/abs/1407.5736v1","url_pdf":"http://arxiv.org/pdf/1407.5736v1.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":[{"paper_slug":"learning-rich-features-from-rgb-d-images-for","repo_url":"https://github.com/charlescxk/depth2hha-python","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-in-indoor-scenes","task_name":"Object Detection In Indoor Scenes"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-in-indoor-scenes-on-sun-rgb","task":"Object Detection In Indoor Scenes","dataset":"SUN RGB-D","model":"RGB-D RCNN (RGB + Depth)","rank_in_archive_order":6,"of":7,"metrics":{"AP 0.5":"44.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1407.5736","atlas_url":"https://app.syntology.ai/?focus=1407.5736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1407.5736"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/charlescxk/depth2hha-python","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"70cf0012537ad543","entry":"computeNormalsSquareSupport","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/rgbd_util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/rgbd_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70cf0012537ad543"}},{"code_sha256_prefix":"4e2bab70ab9e1dd2","entry":"filterItChopOff","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e2bab70ab9e1dd2"}},{"code_sha256_prefix":"1937d93ab08494c9","entry":"getCameraParam","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/getCameraParam.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/getCameraParam.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1937d93ab08494c9"}},{"code_sha256_prefix":"8680262faa681720","entry":"getHHA","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"getHHA.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/getHHA.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8680262faa681720"}},{"code_sha256_prefix":"4ece2819cfdabe15","entry":"getImage","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"getHHA.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/getHHA.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ece2819cfdabe15"}},{"code_sha256_prefix":"e03ae4e68673b53b","entry":"getPointCloudFromZ","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/rgbd_util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/rgbd_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e03ae4e68673b53b"}},{"code_sha256_prefix":"631a071dfd076cde","entry":"invertIt","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"631a071dfd076cde"}},{"code_sha256_prefix":"6905eec587bce8a0","entry":"mutiplyIt","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6905eec587bce8a0"}},{"code_sha256_prefix":"701bd12a124369df","entry":"processDepthImage","repo":"charlescxk/depth2hha-python","repo_kind":"listed","path":"utils/rgbd_util.py","file_url":"https://github.com/charlescxk/depth2hha-python/blob/HEAD/utils/rgbd_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"701bd12a124369df"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}