{"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/excavating-the-potential-capacity-of-self","title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","arxiv_id":"2109.12484","date":"2021-09-26","proceeding":"ICCV 2021 10","authors":["Rui Peng","Ronggang Wang","Yawen Lai","Luyang Tang","Yangang Cai"],"abstract":"Self-supervised methods play an increasingly important role in monocular depth estimation due to their great potential and low annotation cost. To close the gap with supervised methods, recent works take advantage of extra constraints, e.g., semantic segmentation. However, these methods will inevitably increase the burden on the model. In this paper, we show theoretical and empirical evidence that the potential capacity of self-supervised monocular depth estimation can be excavated without increasing this cost. In particular, we propose (1) a novel data augmentation approach called data grafting, which forces the model to explore more cues to infer depth besides the vertical image position, (2) an exploratory self-distillation loss, which is supervised by the self-distillation label generated by our new post-processing method - selective post-processing, and (3) the full-scale network, designed to endow the encoder with the specialization of depth estimation task and enhance the representational power of the model. Extensive experiments show that our contributions can bring significant performance improvement to the baseline with even less computational overhead, and our model, named EPCDepth, surpasses the previous state-of-the-art methods even those supervised by additional constraints.","url_abs":"https://arxiv.org/abs/2109.12484v1","url_pdf":"https://arxiv.org/pdf/2109.12484v1.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":"excavating-the-potential-capacity-of-self","repo_url":"https://github.com/prstrive/EPCDepth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"EPCDepth(S+1024x320)","rank_in_archive_order":7,"of":55,"metrics":{"Delta < 1.25":"0.901","Delta < 1.25^2":"0.966","Delta < 1.25^3":"0.983","Mono":"X","RMSE":"4.207","RMSE log":"0.176","Resolution":"1024x320","Sq Rel":"0.646","absolute relative error":"0.091"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen-1","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split unsupervised","model":"EPCDepth(S+640x192)","rank_in_archive_order":28,"of":55,"metrics":{"Delta < 1.25":"0.888","Delta < 1.25^2":"0.963","Delta < 1.25^3":"0.982","RMSE":"4.490","RMSE log":"0.183","Sq Rel":"0.754","absolute relative error":"0.099"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.12484","atlas_url":"https://app.syntology.ai/?focus=2109.12484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12484"}},"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":"deterministic:regex_extraction","url":"https://github.com/prstrive/EPCDepth","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"bcb368c541b98731","entry":"EncoderDisp","repo":"prstrive/EPCDepth","repo_kind":"official","path":"network/rsu_decoder.py","file_url":"https://github.com/prstrive/EPCDepth/blob/HEAD/network/rsu_decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcb368c541b98731"}},{"code_sha256_prefix":"cd51420fccc186a2","entry":"RSUDecoder","repo":"prstrive/EPCDepth","repo_kind":"official","path":"network/rsu_decoder.py","file_url":"https://github.com/prstrive/EPCDepth/blob/HEAD/network/rsu_decoder.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":"cd51420fccc186a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}