Surf-D introduces a novel method for generating high-quality 3D shapes with arbitrary topologies using diffusion models.
Introducing a novel spatial-aware 3D shape generation framework leveraging hybrid shape representation for enhanced modeling.
Score Distillation Sampling (SDS), a method for generating 3D shapes from 2D diffusion models, often produces blurry and over-smoothed results. This paper reveals that SDS can be understood as a high-variance version of Denoising Diffusion Implicit Models (DDIM) with a different noise sampling strategy. The authors propose Score Distillation via Inversion (SDI), which improves 3D generation quality by replacing the random noise sampling in SDS with a more accurate noise approximation obtained by inverting DDIM.
This paper introduces a novel method for representing and generating 3D shapes using differentiable templates, which parameterize the shared structure of objects within a category and utilize three-view details to capture intricate geometries.
3D形状生成における、従来手法の複雑さや詳細表現の不足といった課題に対し、本論文では、微分可能なテンプレートを用いて部品の構造的関係をパラメータ化することで、詳細な内部構造を持つ多様な3D形状を効率的に再構成および生成する手法を提案している。
이 논문에서는 3D 형상의 공유 구조를 학습 가능한 템플릿으로 파라미터화하여 효율적인 3D 형상 생성 및 재구성을 가능하게 하는 새로운 방법을 제안합니다.