{"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/epipolar-transformers","title":"Epipolar Transformers","arxiv_id":"2005.04551","date":"2020-05-10","proceeding":"CVPR 2020 6","authors":["Yihui He","Rui Yan","Katerina Fragkiadaki","Shoou-I Yu"],"abstract":"A common approach to localize 3D human joints in a synchronized and calibrated multi-view setup consists of two-steps: (1) apply a 2D detector separately on each view to localize joints in 2D, and (2) perform robust triangulation on 2D detections from each view to acquire the 3D joint locations. However, in step 1, the 2D detector is limited to solving challenging cases which could potentially be better resolved in 3D, such as occlusions and oblique viewing angles, purely in 2D without leveraging any 3D information. Therefore, we propose the differentiable \"epipolar transformer\", which enables the 2D detector to leverage 3D-aware features to improve 2D pose estimation. The intuition is: given a 2D location p in the current view, we would like to first find its corresponding point p' in a neighboring view, and then combine the features at p' with the features at p, thus leading to a 3D-aware feature at p. Inspired by stereo matching, the epipolar transformer leverages epipolar constraints and feature matching to approximate the features at p'. Experiments on InterHand and Human3.6M show that our approach has consistent improvements over the baselines. Specifically, in the condition where no external data is used, our Human3.6M model trained with ResNet-50 backbone and image size 256 x 256 outperforms state-of-the-art by 4.23 mm and achieves MPJPE 26.9 mm.","url_abs":"https://arxiv.org/abs/2005.04551v1","url_pdf":"https://arxiv.org/pdf/2005.04551v1.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":"epipolar-transformers","repo_url":"https://github.com/yihui-he/epipolar-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"}],"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":"relu","method_name":"ReLU"},{"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/3d-hand-pose-estimation-on-interhand2-6m","task":"3D Hand Pose Estimation","dataset":"InterHand2.6M","model":"Epipolar Transformers","rank_in_archive_order":1,"of":1,"metrics":{"MPJPE":"4.91"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"Epipolar Transformer+R50 256×256+RPSM","rank_in_archive_order":3,"of":88,"metrics":{"Average MPJPE (mm)":"26.9","Multi-View or Monocular":"Multi-View","Using 2D ground-truth joints":"No"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.04551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04551"}},"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/yihui-he/epipolar-transformers","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"7cf71a41543037fc","entry":"compute_grid","repo":"yihui-he/epipolar-transformers","repo_kind":"official","path":"modeling/pictorial_cuda.py","file_url":"https://github.com/yihui-he/epipolar-transformers/blob/HEAD/modeling/pictorial_cuda.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":"7cf71a41543037fc"}},{"code_sha256_prefix":"a37fc28085305d58","entry":"display_image_in_actual_size","repo":"yihui-he/epipolar-transformers","repo_kind":"official","path":"engine/tester.py","file_url":"https://github.com/yihui-he/epipolar-transformers/blob/HEAD/engine/tester.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":"a37fc28085305d58"}},{"code_sha256_prefix":"722fc78a5d2b270d","entry":"get_loc_from_cube_idx","repo":"yihui-he/epipolar-transformers","repo_kind":"official","path":"modeling/pictorial_cuda.py","file_url":"https://github.com/yihui-he/epipolar-transformers/blob/HEAD/modeling/pictorial_cuda.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":"722fc78a5d2b270d"}},{"code_sha256_prefix":"1b38c039b6c59aa2","entry":"is_rotation_matrix","repo":"yihui-he/epipolar-transformers","repo_kind":"official","path":"vision/camera_model.py","file_url":"https://github.com/yihui-he/epipolar-transformers/blob/HEAD/vision/camera_model.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":"1b38c039b6c59aa2"}},{"code_sha256_prefix":"50525115dcd36e4c","entry":"prefix_modulename","repo":"yihui-he/epipolar-transformers","repo_kind":"official","path":"utils/ext_model_loading.py","file_url":"https://github.com/yihui-he/epipolar-transformers/blob/HEAD/utils/ext_model_loading.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":"50525115dcd36e4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}