SeMo3D unifies 3D generation editing and completion
SeMo3D uses selective modeling to unify 3D tasks with region-selective denoising and Omni3DiT architecture.
3 stories, newest first · one card per story
SeMo3D uses selective modeling to unify 3D tasks with region-selective denoising and Omni3DiT architecture.
EditHero benchmarks long-horizon part-level 3D editing, finding LLM/VLM agents follow instructions and preserve untouched regions better but edit far slower.
New framework distills 2D editing and VLM priors into a feed-forward 3D editing model without paired 3D training data.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views