Papers › Epipolar Transformers

Epipolar Transformers

10 May 2020CVPR 2020 6arXiv:2005.04551archive 2025-07-28

Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2005.04551")

Code

Syntology Ran 0 of 5 code samples harvested from 1 repository linked to this paper; 5 have no recorded run.

By repository: official repository: 5 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yihui-he/epipolar-transformers officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested; 0 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yihui-he/epipolar-transformers. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_grid yihui-he/epipolar-transformers/modeling/pictorial_cuda.py official repository unverified MIT (permissive) · 7cf71a41543037fc · report
display_image_in_actual_size yihui-he/epipolar-transformers/engine/tester.py official repository unverified MIT (permissive) · a37fc28085305d58 · report
get_loc_from_cube_idx yihui-he/epipolar-transformers/modeling/pictorial_cuda.py official repository unverified MIT (permissive) · 722fc78a5d2b270d · report
is_rotation_matrix yihui-he/epipolar-transformers/vision/camera_model.py official repository unverified MIT (permissive) · 1b38c039b6c59aa2 · report
prefix_modulename yihui-he/epipolar-transformers/utils/ext_model_loading.py official repository unverified MIT (permissive) · 50525115dcd36e4c · report

Tasks

2D Pose Estimation3D Hand Pose Estimation3D Human Pose Estimation3D Pose EstimationPose EstimationStereo Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation InterHand2.6M Epipolar Transformers MPJPE 4.91 #1 of 1 Archive leaderboard report
3D Human Pose Estimation Human3.6M Epipolar Transformer+R50 256×256+RPSM Average MPJPE (mm) 26.9 #3 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Epipolar Transformer+R50 256×256+RPSM Multi-View or Monocular Multi-View #3 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Epipolar Transformer+R50 256×256+RPSM Using 2D ground-truth joints No #3 of 88 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections