Tag
This paper presents a method to reconstruct 3D bone geometry from two X-ray silhouettes using a statistical shape model and differentiable rendering.
DiffGI introduces a differentiable geometry image representation for high-fidelity thin-shell 3D generation, enabling end-to-end optimization and superior reconstruction quality.
This paper proposes a feed-forward framework that decomposes 3D scenes into instance-structured token groups from unposed multi-view images, enabling direct object-level reconstruction, segmentation, and manipulation without 3D annotations.
FLAT proposes a method to decode explicit triangle splats directly from video diffusion latents for geometrically accurate 3D scene generation. It introduces a ray-centered rotation parameterization and a product window function to improve gradient flow, achieving better geometric accuracy than prior feedforward methods while supporting real-time rendering.