Author

Chen-Ming Zhu

h-index 13 View on Semantic Scholar

We have 2 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

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

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 geo...

Yi-Lin Long, Chen-Ming Zhu, Zi-Tang Gou et al. · 0 citations

Jul 2026

G2TAM: Geometry Grounded Track Anything Model

The Geometry Grounded Tracking Anything Model is proposed, a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos and delivers strong cross-view consistency, promptable instance spatial tracking, video object segmentation and spatial reconstruction, establishing a foundatio...

Chen-Ming Zhu, Peizhou Cao, Jing-Li Lin et al. · arXiv.org · 0 citations