arXiv Computer Vision

MetricPose: Flexible 3D Human Pose Estimation with Depth and Geometric Cues

MetricPose is a 3D human pose estimator that predicts metrically accurate joint positions in the camera coordinate frame by combining learned RGB priors, direct depth measurements, and geometric constraints such as ground contact. The model extends a pretrained full-body estimator with optional metric depth and geometry-processing modules, enabling unified support for RGB, RGB‑Ground, and RGB‑D inputs while preserving RGB‑only operation. Compared to the SAM 3D Body foundation model, MetricPose reduces camera‑local joint‑position error by 12.16%, 31.00%, and 54.61% in RGB, RGB‑Ground, and RGB‑D modes respectively.

arXiv AI
Oct 31

SituHOI: Scalable Capture of Scene-Situated Full-Body Human-Object Interaction

SituHOI is a large‑scale RGB‑D dataset that captures full‑body human‑object interactions in 16 indoor rooms, comprising 18,429 annotated clips and about 86 hours of activity. The dataset pairs moving‑camera recordings with static scene scans, object geometry, language descriptions, and estimated human and object trajectories, all registered in a shared floor‑aligned frame via a pipeline that integrates camera localization, depth‑based alignment, human mesh recovery, and object tracking. The data enable the FlexHOI‑Bench benchmark for goal‑conditioned joint motion prediction, and a reference predictor, SharedHOI, demonstrates strong performance on world‑space accuracy and human‑object coordination. whyItMatters":"The dataset provides scalable, scene‑aligned supervision for modeling human‑object interaction, addressing a key limitation of existing datasets and enabling more accurate motion prediction benchmarks."

By Qifan Wang, Qihang Fang, Boao Shi, Yushi Du, Pei Zhou, Siyan Dong, Yanchao Yang
arXiv Computer Vision
Nov 6

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.

By Charles Javerliat, Pierre Raimbaud, Guillaume Lavou\'e