collaborators

6 papers

cs.CV2026

Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis

Jhacson Meza, Martin R. Oswald, Torsten Sattler

Novel view synthesis (NVS) approaches such as NeRFs or 3DGS can produce photo-realistic 3D scene representation from a set of images with known extrinsic and intrinsic parameters.…

cs.CV2026

From Rays to Projections: Better Inputs for Feed-Forward View Synthesis

Zirui Wu, Zeren Jiang, Martin R. Oswald +1

Feed-forward view synthesis models predict a novel view in a single pass with minimal 3D inductive bias. Existing works encode cameras as Plücker ray maps, which tie predictions t…

cs.CV2025

Physics-based Human Pose Estimation from a Single Moving RGB Camera

Ayce Idil Aytekin, Chuqiao Li, Diogo Luvizon +4

Most monocular and physics-based human pose tracking methods, while achieving state-of-the-art results, suffer from artifacts when the scene does not have a strictly flat ground pl…

cs.CV2025

ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos

Zetong Zhang, Manuel Kaufmann, Lixin Xue +2

Creating a photorealistic scene and human reconstruction from a single monocular in-the-wild video figures prominently in the perception of a human-centric 3D world. Recent neural…

cs.GR2025

3D Gaussian Inverse Rendering with Approximated Global Illumination

Zirui Wu, Jianteng Chen, Laijian Li +5

3D Gaussian Splatting shows great potential in reconstructing photo-realistic 3D scenes. However, these methods typically bake illumination into their representations, limiting the…

cs.CV2025

WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

Tianjian Jiang, Johsan Billingham, Sebastian Müksch +7

We present WorldPose, a novel dataset for advancing research in multi-person global pose estimation in the wild, featuring footage from the 2022 FIFA World Cup. While previous data…