{"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/motion-based-object-segmentation-based-on","title":"Motion-based Object Segmentation based on Dense RGB-D Scene Flow","arxiv_id":"1804.05195","date":"2018-04-14","proceeding":null,"authors":["Lin Shao","Parth Shah","Vikranth Dwaracherla","Jeannette Bohg"],"abstract":"Given two consecutive RGB-D images, we propose a model that estimates a dense\n3D motion field, also known as scene flow. We take advantage of the fact that\nin robot manipulation scenarios, scenes often consist of a set of rigidly\nmoving objects. Our model jointly estimates (i) the segmentation of the scene\ninto an unknown but finite number of objects, (ii) the motion trajectories of\nthese objects and (iii) the object scene flow. We employ an hourglass, deep\nneural network architecture. In the encoding stage, the RGB and depth images\nundergo spatial compression and correlation. In the decoding stage, the model\noutputs three images containing a per-pixel estimate of the corresponding\nobject center as well as object translation and rotation. This forms the basis\nfor inferring the object segmentation and final object scene flow. To evaluate\nour model, we generated a new and challenging, large-scale, synthetic dataset\nthat is specifically targeted at robotic manipulation: It contains a large\nnumber of scenes with a very diverse set of simultaneously moving 3D objects\nand is recorded with a simulated, static RGB-D camera. In quantitative\nexperiments, we show that we outperform state-of-the-art scene flow and\nmotion-segmentation methods on this data set. In qualitative experiments, we\nshow how our learned model transfers to challenging real-world scenes, visually\ngenerating better results than existing methods.","url_abs":"http://arxiv.org/abs/1804.05195v2","url_pdf":"http://arxiv.org/pdf/1804.05195v2.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":"motion-based-object-segmentation-based-on","repo_url":"https://github.com/stanford-iprl-lab/sceneflownet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"motion-segmentation","task_name":"Motion Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.05195"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/stanford-iprl-lab/sceneflownet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"a1c99ce409c56354","entry":"angleaxis_rotmatrix","repo":"stanford-iprl-lab/sceneflownet","repo_kind":"listed","path":"segNet2/tf_libs/sceneflownet_experiment_corr.py","file_url":"https://github.com/stanford-iprl-lab/sceneflownet/blob/HEAD/segNet2/tf_libs/sceneflownet_experiment_corr.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":"a1c99ce409c56354"}},{"code_sha256_prefix":"56cad31aceab1ab5","entry":"quaternion_multiply","repo":"stanford-iprl-lab/sceneflownet","repo_kind":"listed","path":"segNet2/models/sceneflownet.py","file_url":"https://github.com/stanford-iprl-lab/sceneflownet/blob/HEAD/segNet2/models/sceneflownet.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":"56cad31aceab1ab5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}