arXiv Computer Vision
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
1d ago
Monocular Visual Odometry without Calibration or Test-time Optimization
arXiv:2510.03348v5 Announce Type: replace Abstract: The most accurate monocular visual odometry systems require known camera intrinsics, refine their estimates with test-time optimization, and recove...
arXiv Computer Vision
Sep 11
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
The paper introduces EgoGenEval, a new benchmark that assesses the physical consistency of visual generators under ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. Experiments on 16 pose‑free generators and two pose‑conditioned references show that current models struggle to maintain both camera motion and scene state simultaneously. A follow‑up study using EgoGen‑Train demonstrates that pairwise supervision does not effectively improve both metrics together, suggesting the need for a trajectory‑centric training paradigm.
Hugging Face Trending Papers
Sep 10
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
The paper introduces EgoGenEval, a benchmark that assesses visual generators’ physical consistency during ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. It shows that current pose‑free models struggle to maintain both camera motion and scene state, and that pairwise supervision in training does not simultaneously improve these aspects. The authors suggest a trajectory‑centric approach that couples self‑conditioned rollouts with explicit pose and visibility supervision to address these limitations.
arXiv Computer Vision
Sep 1
XDG: Accelerated Visual Disambiguation
arXiv:2608.29733v1 Announce Type: new Abstract: Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically disti...
arXiv Computer Vision
4d ago
MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons
arXiv:2604.28130v4 Announce Type: replace Abstract: Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts join...
Hugging Face Trending Papers
2d ago
GeoCond: A Conditioning-Aware Reliability Adapter for Feed-Forward 3D Reconstruction
Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low parallax, and extreme relative rotation. Stratified...