Skip to content
AI Atlas
PaperActive

Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval

arxiv.org/abs/2609.11172

Updated 51 min ago · first seen 11 Sept 2026

paper_01M294H1VBMMZGV4C4F0TASRF7

Published
11 Sept 2026
T1 · 51 min ago
arXiv
2609.11172
T1 · 51 min ago
Category
cs.CV
T1 · 51 min ago

Abstract

Recent visual generators produce high-fidelity images yet often violate physical consistency under ego-motion, limiting their use for spatial reasoning and embodied planning. Existing benchmarks largely focus on isolated images or single-step quality, leaving this challenge underexplored. We introduce EgoGenEval, a geometry-grounded, pose-free benchmark designed to evaluate the physical consistency of visual generators under ego-motion, and organize our study into two parts. (1) EgoGenEval contains 1,400 cases and 2,360 target views spanning single-step and multi-step ego-motion. It separately measures Camera Motion Grounding (CMG) and Scene State Preservation (SSP), with both metrics validated against blinded human judgments. Evaluating 16 pose-free generators together with two pose-conditioned references reveals that current models struggle to execute camera motion while maintaining scene state, and that no system performs well on both axes at once. (2) To examine whether benchmark-derived data can improve these capabilities, we build EgoGen-Train from the same geometry-grounded pipeline and run controlled SFT studies. These show that pairwise supervision does not reliably improve camera-motion grounding and scene-state preservation together: even at the full training pool and the longest budget, scene preservation gains a fraction of what camera motion does. This points to the pairwise teacher-forced objective itself as the binding constraint, motivating a trajectory-centric paradigm that couples self-conditioned rollouts with explicit pose and visibility supervision.

Authors 5

Yilin Long, Chenming Zhu, Zitang Gou, Jingli Lin, Tai Wang

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Arxiv announce type
new

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

arXiv id
2609.11172

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Categories
cs.CV, cs.AI

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Primary category
cs.CV

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

51 min ago

Conflicts

None