{"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/urcdc-depth-uncertainty-rectified-cross","title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","arxiv_id":"2302.08149","date":"2023-02-16","proceeding":null,"authors":["Shuwei Shao","Zhongcai Pei","Weihai Chen","Ran Li","Zhong Liu","Zhengguo Li"],"abstract":"This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and the local information is critical for accurate depth estimation. Towards this end, we introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural network (CNN) to learn a unified depth estimator. Specifically, we use the depth estimates from the Transformer branch and the CNN branch as pseudo labels to teach each other. Meanwhile, we model the pixel-wise depth uncertainty to rectify the loss weights of noisy pseudo labels. To avoid the large capacity gap induced by the strong Transformer branch deteriorating the cross-distillation, we transfer the feature maps from Transformer to CNN and design coupling units to assist the weak CNN branch to leverage the transferred features. Furthermore, we propose a surprisingly simple yet highly effective data augmentation technique CutFlip, which enforces the model to exploit more valuable clues apart from the vertical image position for depth inference. Extensive experiments demonstrate that our model, termed~\\textbf{URCDC-Depth}, exceeds previous state-of-the-art methods on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets, even with no additional computational burden at inference time. The source code is publicly available at \\url{https://github.com/ShuweiShao/URCDC-Depth}.","url_abs":"https://arxiv.org/abs/2302.08149v2","url_pdf":"https://arxiv.org/pdf/2302.08149v2.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":"urcdc-depth-uncertainty-rectified-cross","repo_url":"https://github.com/shuweishao/urcdc-depth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"URCDC-Depth","rank_in_archive_order":20,"of":79,"metrics":{"Delta < 1.25":"0.977","Delta < 1.25^2":"0.997","Delta < 1.25^3":"0.999","RMSE":"2.032","RMSE log":"0.076","Sq Rel":"0.142","absolute relative error":"0.050"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"URCDC-Depth","rank_in_archive_order":36,"of":85,"metrics":{"Delta < 1.25":"0.933","Delta < 1.25^2":"0.992","Delta < 1.25^3":"0.998","RMSE":"0.316","absolute relative error":"0.088","log 10":"0.038"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.08149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08149"}},"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/shuweishao/urcdc-depth","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran":2,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/newcrf_layers.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/newcrf_layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"050c56fb7282eb88","entry":"get_num_lines","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"050c56fb7282eb88"}},{"code_sha256_prefix":"8a05ea4d5e917bf4","entry":"normalize_result","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a05ea4d5e917bf4"}},{"code_sha256_prefix":"35e6bae6a3fe0669","entry":"upsample","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/NewCRFDepth.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/NewCRFDepth.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35e6bae6a3fe0669"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/newcrf_layers.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/newcrf_layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"9999af2cf9c1b6bb","entry":"colorize","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/utils.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":"9999af2cf9c1b6bb"}},{"code_sha256_prefix":"9b9dd29ad0d626a0","entry":"is_module_wrapper","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/newcrf_utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/newcrf_utils.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":"9b9dd29ad0d626a0"}},{"code_sha256_prefix":"92dad73ee855852f","entry":"load_url_dist","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/newcrf_utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/newcrf_utils.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":"92dad73ee855852f"}},{"code_sha256_prefix":"4f7c1c530e5b46be","entry":"preprocessing_transforms","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/dataloaders/dataloader.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/dataloaders/dataloader.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":"4f7c1c530e5b46be"}},{"code_sha256_prefix":"ea623328271af85a","entry":"preprocessing_transforms","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/dataloaders/dataloader_kittipred.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/dataloaders/dataloader_kittipred.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":"ea623328271af85a"}},{"code_sha256_prefix":"9012d3fdd4cbaea1","entry":"resize","repo":"shuweishao/urcdc-depth","repo_kind":"official","path":"urcdc/networks/newcrf_utils.py","file_url":"https://github.com/shuweishao/urcdc-depth/blob/HEAD/urcdc/networks/newcrf_utils.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":"9012d3fdd4cbaea1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}