arXiv Computer Vision By Tzu-Yuan Lin, Ho Jae Lee, Kevin Doherty, Yonghyeon Lee, Sangbae Kim

Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers

Read the original on arXiv Computer Vision →

Point2Pose is a model‑free method for causal 6D pose tracking of multiple rigid objects using monocular RGB‑D video. It starts from sparse image points and employs a 2D point tracker to maintain long‑range correspondences, allowing instant recovery after complete occlusion. The system also incrementally builds an online Truncated Signed Distance Function (TSDF) representation of the tracked objects and introduces a new multi‑object tracking dataset with motion‑capture ground truth.

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.

Hugging Face Trending Papers
Jun 24

MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation

Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelity with respect to the reference video. Existing methods based on explicit 3D representations are limited by the accuracy of off-the-shelf reconstruction modules, which often produce inaccurate geometry for dynamic objects in monocular videos.