Papers › EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular...
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
Hansheng Chen, Pichao Wang, Fan Wang, Wei Tian, Lu Xiong, Hao Li
Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | NDS | 0.453 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mAAE | 0.124 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mAOE | 0.359 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mAP | 0.373 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mASE | 0.243 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mATE | 0.605 | #309 of 372 | Archive leaderboard | report |
| 3D Object Detection | nuScenes | EPro-PnP-Det v1 | mAVE | 1.067 | #309 of 372 | Archive leaderboard | report |
| 6D Pose Estimation using RGB | LineMOD | EPro-PnP-6DoF v1 | Mean ADD | 95.8 | #6 of 22 | 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
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