Hugging Face Trending Papers
XM4D: 4D Reconstruction through Certifiable Geometric Optimization
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
22h ago
XM4D: 4D Reconstruction through Certifiable Geometric Optimization
XM4D is a new framework for accurate 4D reconstruction that separates camera motion estimation from non‑rigid deformation. Both stages are cast as structured quadratically constrained quadratic programs (QCQPs) with semidefinite programming (SDP) relaxations, enabling certifiable global optimality. The method uses GPU‑accelerated Burer‑Monteiro solvers, initializes dynamic Gaussian splatting for refinement, and achieves state‑of‑the‑art performance on seven benchmarks.
arXiv AI
Oct 21
RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction
arXiv:2610.28351v1 Announce Type: cross Abstract: Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks...
arXiv Computer Vision
22h ago
Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras
Kineo is a fully automatic, calibration‑free pipeline that performs markerless motion capture using unsynchronized, uncalibrated consumer‑grade RGB cameras. It uses 2D keypoints from existing detectors to jointly calibrate cameras (including distortion), reconstruct 3D keypoints, and generate dense scene pointmaps at metric scale. The method introduces confidence‑aware subsampling, graph‑based optimization, and a pairwise reprojection consistency score to achieve robust calibration and accurate metric scale recovery, achieving significant error reductions on EgoHumans and Human3.6M datasets while remaining computationally efficient.
Hugging Face Trending Papers
Oct 8
PointVGGT: Zero-Shot Multiview RGB-D Point Cloud Registration with Visual Geometry Foundation Priors
The paper introduces PointVGGT, a zero‑shot framework for multiview RGB‑D point cloud registration that avoids pairwise estimation by using a foundation‑then‑refinement paradigm. In the foundation stage, it recovers metrically consistent global poses by grounding scale‑ambiguous predictions from visual geometry foundation models against metric depth. The refinement stage employs voxelized spatial hashing and IRLS‑based bundle adjustment to efficiently refine poses, achieving high accuracy and computational efficiency across indoor, object‑centric, and outdoor datasets.
arXiv Computer Vision
Oct 9
PointVGGT: Zero-Shot Multiview RGB-D Point Cloud Registration with Visual Geometry Foundation Priors
The paper introduces PointVGGT, a zero‑shot framework for multiview RGB‑D point cloud registration that replaces the traditional pairwise‑then‑global pipeline. It employs a foundation‑then‑refinement paradigm, using visual geometry foundation models to directly recover metrically consistent global poses and then refining them with voxelized spatial hashing and IRLS‑based bundle adjustment. Experiments on indoor, object‑centric, and outdoor datasets demonstrate superior registration accuracy and computational efficiency without any training.
arXiv Computer Vision
22h ago
SM4RT: Cascaded Feed-forward Model for 4D Reconstruction
arXiv:2611.08436v1 Announce Type: new Abstract: We introduce SM4RT, a multi-task cascade feed-forward model for dynamic scene reconstruction from RGB videos. While existing feed-forward approaches ty...