arXiv:2610.38358 · v1

Volley3D: Unified 3D Full-Sequence Reconstruction from Monocular Broadcasts

首次提交 2026-10-28 14:56

版本更新 2026-10-28 14:56

雷达观测 2026-10-30 10:22

摘要

3D reconstruction from single-view sports broadcast is a pivotal capability for automated analytics and immersive AR/VR replays, yet notoriously ill-posed due to difficult-to-calibrate moving cameras and depth ambiguity. Unlike widely studied racket sports, team sports such as volleyball feature unpredictable multi-contact sequences and high altitude jumps. These dynamics categorically invalidate the standard planar projection assumptions relied upon by existing methods. To resolve these limitations without 3D training supervision, we propose a complete, physics-grounded pipeline tailored to monocular broadcast volleyball. First, we include a correction module to the perspective drift induced by ground-plane projection by coupling temporal jump spotting with Newtonian interpolation for 3D player placement. Second, for 3D ball trajectory estimation, we design a dedicated sub-trajectory segmentation architecture alongside a collision-matching algorithm. By anchoring physical equations to reconstructed 3D hand vertices, we lift noisy ball 2D detections into a spatiotemporally coherent 3D scene. Evaluations on multi-camera benchmarks demonstrate our approach significantly reduces 3D spatial drift compared to 2D-reprojection baselines.

作者备注：8 pages + 10 pages of supplementary. Videos available on the project webpage: noambsf.github.io/Volley3D