WildHSR introduces a lightweight adaptation of 3D foundation models to jointly recover metric cameras, scene geometry, and persistent person identities from monocular video. By generating pseudo‑scale labels from curated web footage and fine‑tuning a Scale Readout, the method predicts metric scale directly from foundation‑model tokens. It also exploits intermediate query‑key features to associate per‑frame bodies, enabling feed‑forward reconstruction that outperforms state‑of‑the‑art optimization‑based methods on several benchmarks while running at 10.1 fps.
arXiv:2603.12789v3 Announce Type: replace Abstract: Recent advances in 3D foundation models have enabled joint reconstruction of humans and their surrounding environments. However, combining independ...
arXiv:2609.01276v1 Announce Type: new Abstract: Complete 3D perception from egocentric video requires recovering the surrounding scene and the wearer's full-body motion in a shared metric frame. Exis...
arXiv:2605.14854v3 Announce Type: replace-cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evide...
Human mesh recovery (HMR) aims to recover 3D human meshes from images. Most existing HMR benchmarks and methods focus on either multi-person reconstruction from a single view or single-person reconstruction from multiple views, where the number of subjects and the scene scale are relatively limited.
Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories.
arXiv:2609.36937v1 Announce Type: cross Abstract: Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation,...
arXiv:2606. 11670v1 Announce Type: cross Abstract: Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large viewpoint changes, expression shifts, occlusion, scale variation, and conflicts among text, first-frame, and identity references.
The paper introduces a top‑down approach for multi‑person 3D reconstruction from multiple views, using a unified, instance‑centric human‑aware 3D space. Observations from different cameras are lifted into this shared space where geometry, appearance, and semantic cues are jointly encoded, and a spatial contrastive learning strategy aligns features of the same person across views while separating different individuals. The method then regresses SMPL parameters from 3D tokens in a feed‑forward manner, achieving robust, accurate, and efficient reconstruction even under severe occlusions.
arXiv:2609.24482v1 Announce Type: new Abstract: Monocular 3D human pose estimation (HPE) remains challenging due to depth ambiguity, occlu- sions, and the need for temporal consistency. While multi-v...
arXiv:2609.15032v1 Announce Type: new Abstract: Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either r...
arXiv:2609.39748v1 Announce Type: new Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...
MINT is a foundation model that directly predicts world-space two-hand trajectories from egocentric RGB video, jointly estimating camera motion, hand states, and hand presence in a single spatiotemporal representation. It uses an open-source labeling pipeline, EGOPIPELINE, to generate large-scale pseudo-labels for pretraining, followed by fine-tuning on a small set of high-quality joint annotations. The model outperforms existing multi-stage approaches in accuracy and speed, and generalizes zero‑shot to unseen egocentric datasets.