Skip to main content
← All papers

A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)

Asaria, Salomone, GandhiΒ·June 16, 20263DVISION

A standardized evaluation protocol for single-image-to-3D mesh generators, using 24-view rendering and position-bias correction β€” and showing that common proxies like CLIP similarity and geometry-validity metrics don't substitute for a VLM judge.

Your browser can’t display the PDF inline. Download it instead.