{"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/neural-rgb-d-sensing-depth-and-uncertainty","title":"Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera","arxiv_id":"1901.02571","date":"2019-01-09","proceeding":null,"authors":["Chao Liu","Jinwei Gu","Kihwan Kim","Srinivasa Narasimhan","Jan Kautz"],"abstract":"Depth sensing is crucial for 3D reconstruction and scene understanding.\nActive depth sensors provide dense metric measurements, but often suffer from\nlimitations such as restricted operating ranges, low spatial resolution, sensor\ninterference, and high power consumption. In this paper, we propose a deep\nlearning (DL) method to estimate per-pixel depth and its uncertainty\ncontinuously from a monocular video stream, with the goal of effectively\nturning an RGB camera into an RGB-D camera. Unlike prior DL-based methods, we\nestimate a depth probability distribution for each pixel rather than a single\ndepth value, leading to an estimate of a 3D depth probability volume for each\ninput frame. These depth probability volumes are accumulated over time under a\nBayesian filtering framework as more incoming frames are processed\nsequentially, which effectively reduces depth uncertainty and improves\naccuracy, robustness, and temporal stability. Compared to prior work, the\nproposed approach achieves more accurate and stable results, and generalizes\nbetter to new datasets. Experimental results also show the output of our\napproach can be directly fed into classical RGB-D based 3D scanning methods for\n3D scene reconstruction.","url_abs":"http://arxiv.org/abs/1901.02571v1","url_pdf":"http://arxiv.org/pdf/1901.02571v1.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":"neural-rgb-d-sensing-depth-and-uncertainty","repo_url":"https://github.com/NVlabs/neuralrgbd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-scene-reconstruction","task_name":"3D Scene Reconstruction"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.02571","atlas_url":"https://app.syntology.ai/?focus=1901.02571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02571"}},"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/NVlabs/neuralrgbd","reach":null}],"summary":{"ran_violates":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"9fe2bdd3093c8e07","entry":"check_datArray_pose","repo":"NVlabs/neuralrgbd","repo_kind":"listed","path":"code/train_KVNet.py","file_url":"https://github.com/NVlabs/neuralrgbd/blob/HEAD/code/train_KVNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9fe2bdd3093c8e07"}},{"code_sha256_prefix":"17f1aa4547ebb492","entry":"check_datArray_pose","repo":"NVlabs/neuralrgbd","repo_kind":"listed","path":"code/test_KVNet.py","file_url":"https://github.com/NVlabs/neuralrgbd/blob/HEAD/code/test_KVNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"17f1aa4547ebb492"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}