{"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/df-net-unsupervised-joint-learning-of-depth","title":"DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency","arxiv_id":"1809.01649","date":"2018-09-05","proceeding":"ECCV 2018 9","authors":["Yuliang Zou","Zelun Luo","Jia-Bin Huang"],"abstract":"We present an unsupervised learning framework for simultaneously training\nsingle-view depth prediction and optical flow estimation models using unlabeled\nvideo sequences. Existing unsupervised methods often exploit brightness\nconstancy and spatial smoothness priors to train depth or flow models. In this\npaper, we propose to leverage geometric consistency as additional supervisory\nsignals. Our core idea is that for rigid regions we can use the predicted scene\ndepth and camera motion to synthesize 2D optical flow by backprojecting the\ninduced 3D scene flow. The discrepancy between the rigid flow (from depth\nprediction and camera motion) and the estimated flow (from optical flow model)\nallows us to impose a cross-task consistency loss. While all the networks are\njointly optimized during training, they can be applied independently at test\ntime. Extensive experiments demonstrate that our depth and flow models compare\nfavorably with state-of-the-art unsupervised methods.","url_abs":"http://arxiv.org/abs/1809.01649v1","url_pdf":"http://arxiv.org/pdf/1809.01649v1.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":"df-net-unsupervised-joint-learning-of-depth","repo_url":"https://github.com/vt-vl-lab/DF-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"depth-and-camera-motion","task_name":"Depth And Camera Motion"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.01649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.01649"}},"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/vt-vl-lab/DF-Net","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"cd478255d97170bb","entry":"pick_frame","repo":"vt-vl-lab/DF-Net","repo_kind":"official","path":"test_flownet_2012.py","file_url":"https://github.com/vt-vl-lab/DF-Net/blob/HEAD/test_flownet_2012.py","link_basis":"first_harvest_node","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":"cd478255d97170bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}