arXiv Computer Vision
Sep 2

Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation

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.

By Yuanwang Yang, Buzhen Huang, Zongxuan Ren, Jing Huang, Kun Li
arXiv Computer Vision
Oct 9

GenIA: Generative Reconstruction with Test-Time Input Alignment

GenIA is a framework that aligns generative 3D foundation models with test‑time observations, improving pose estimation and reconstruction from monocular, multi‑view, and dynamic inputs. It derives translation and scale from geometry, retains learned rotation priors, and aligns appearance using visibility‑biased attention, cross‑observation fusion, and differentiable rendering guidance during denoising. An optional post‑denoising refinement further adapts appearance latents and object placement, and the method also supports externally supplied geometry for dynamic objects, achieving better results than recent optimization‑based and image‑to‑3D methods on synthetic and real benchmarks.

By Stefano Esposito, Naama Pearl, Polina Karpikova, Samuel Rota Bul\`o, Lorenzo Porzi, Peter Kontschieder, Andreas Geiger, Jonathon Luiten
arXiv AI
Sep 25

WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model

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.

By Jerrin Bright, John Zelek