{"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/demon-depth-and-motion-network-for-learning","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","arxiv_id":"1612.02401","date":"2016-12-07","proceeding":"CVPR 2017 7","authors":["Benjamin Ummenhofer","Huizhong Zhou","Jonas Uhrig","Nikolaus Mayer","Eddy Ilg","Alexey Dosovitskiy","Thomas Brox"],"abstract":"In this paper we formulate structure from motion as a learning problem. We\ntrain a convolutional network end-to-end to compute depth and camera motion\nfrom successive, unconstrained image pairs. The architecture is composed of\nmultiple stacked encoder-decoder networks, the core part being an iterative\nnetwork that is able to improve its own predictions. The network estimates not\nonly depth and motion, but additionally surface normals, optical flow between\nthe images and confidence of the matching. A crucial component of the approach\nis a training loss based on spatial relative differences. Compared to\ntraditional two-frame structure from motion methods, results are more accurate\nand more robust. In contrast to the popular depth-from-single-image networks,\nDeMoN learns the concept of matching and, thus, better generalizes to\nstructures not seen during training.","url_abs":"http://arxiv.org/abs/1612.02401v2","url_pdf":"http://arxiv.org/pdf/1612.02401v2.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":"demon-depth-and-motion-network-for-learning","repo_url":"https://github.com/SuryaKalia/AaltoVision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"demon-depth-and-motion-network-for-learning","repo_url":"https://github.com/lmb-freiburg/demon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-and-camera-motion","task_name":"Depth And Camera Motion"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.02401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.02401"}},"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/lmb-freiburg/demon","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SuryaKalia/AaltoVision","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":"88371c3f046ad6a9","entry":"float_to_binary","repo":"SuryaKalia/AaltoVision","repo_kind":"listed","path":"Part2/example_edit.py","file_url":"https://github.com/SuryaKalia/AaltoVision/blob/HEAD/Part2/example_edit.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":"88371c3f046ad6a9"}},{"code_sha256_prefix":"262cc5a681c60870","entry":"prepare_input_data","repo":"SuryaKalia/AaltoVision","repo_kind":"listed","path":"Part2/example_edit.py","file_url":"https://github.com/SuryaKalia/AaltoVision/blob/HEAD/Part2/example_edit.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":"262cc5a681c60870"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}