arXiv Computer Vision By Huiting Xi, Marsha Mariya Kappan, Eduardo Benitez Sandoval, Francisco Cruz

CJRR-Net: A Candidate-Joint Reprojection Ranking for Future-View Selection in Human Pose Estimation

Read the original on arXiv Computer Vision →

The paper introduces CJRR-Net, a network designed to select the most informative camera view for human pose estimation in multi‑camera setups. It uses current‑view pose data, camera layout, and geometric features derived from reprojecting the estimated 3D pose and its uncertainty into each candidate view. In experiments on the MPI‑INF‑3DHP dataset, CJRR‑Net outperforms baseline methods, achieving a 2D mean per‑joint position error of 105.18 pixels and the lowest error across occlusion groups.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI
3d ago

Multi-View 3D Reconstruction Using V-JEPA Features

The paper investigates supervised RGB‑only multi‑view 3D reconstruction by integrating video‑pretrained features with camera estimation, scene aggregation, epipolar transport, and residual pointmaps. Experiments on CO3D and indoor datasets compare global versus spatial camera regression and a joint relative‑objective configuration, reporting improvements in trajectory and intrinsics errors but mixed effects on depth accuracy and raw Chamfer distance. The results emphasize that representation adaptation, shape alignment, and raw reconstruction must be evaluated separately before attributing gains to predictive video pretraining.

By Anwar Shamim, Jeffrin Sam
arXiv Computer Vision
Oct 28

UT-HMR: Uncertainty-Guided Temporal Modeling for Robust 3D Human Mesh Recovery

UT‑HMR is a one‑stage monocular 3D human mesh recovery framework that introduces uncertainty‑guided temporal modeling to address ambiguities caused by weak observations such as distance, occlusion, and motion blur. It predicts a Gaussian distribution over SMPL pose with a low‑rank-plus‑diagonal covariance, converting this into joint‑wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion incorporates neighboring‑frame evidence before pose decoding, enabling the model to resolve pose ambiguities and achieve state‑of‑the‑art results on VIP‑HockeyPose‑v2, WorldPose, and competitive performance on 3DPW using a lightweight ViT‑B backbone.

By Zhibo Wang, Sirisha Rambhatla, Yuhao Chen, Maria Koshkina, David Clausi
Hugging Face Trending Papers
6d ago

Multi-View 3D Reconstruction Using V-JEPA Features

The paper investigates supervised RGB‑only multi‑view 3D reconstruction by leveraging video‑pretrained features and a pipeline that includes camera estimation, scene aggregation, epipolar transport, and residual pointmaps. Experiments on CO3D and indoor datasets compare global versus spatial camera regression and a joint relative‑objective configuration, revealing trade‑offs in trajectory, depth, and Chamfer distance metrics. The results emphasize that improvements in reconstruction stem from specific representation adaptations and component interactions rather than solely from predictive video pretraining.