
Yanpei Cao
@yanpei_cao • 2,275 subscribers
Chief Scientist @VastAIResearch @tripoai. Prev: Principal Researcher @TencentGlobal, Kuaishou (HKG:1024), CTO @OwliiTech (acq. by Kuaishou), @Tsinghua_Uni.
Shorts
Videos

3D generation often treats objects as single, monolithic shapes. Our new research, OmniPart, takes a different path: generating objects as assemblies of parts for structural coherence and fine-grained control. And it has been accepted to SIGGRAPH Asia 2025 🎉
Yanpei Cao222,302 просмотров • 9 месяцев назад

Generative 3D has been stuck in a representational compromise. When you serialize spatial data to fit standard architectures, you force a unidirectional causal bias. It fundamentally breaks the symmetry of 3D geometry and limits how the model understands global context. With Tripo P1.0, we stepped back to fix the representation. Instead of flattening 3D into sequences, P1.0 operates entirely within a native spatial probability space. It reasons about the entire structure at once. That’s why the topology actually makes sense. We aren't running a post-process remesher to clean up artifacts. When you directly model the structured surface manifold, clean edge flows and structural coherence naturally emerge from the noise. This is what happens when the architecture finally respects the medium. And we are doing it in 2 seconds.
Yanpei Cao65,243 просмотров • 4 месяцев назад
Больше нет контента для загрузки