Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
Surf-D introduces a novel method for generating high-quality 3D shapes with arbitrary topologies using diffusion models.
NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Introducing a novel spatial-aware 3D shape generation framework leveraging hybrid shape representation for enhanced modeling.
Improving 3D Shape Generation with Diffusion Models by Inverting the Denoising Process
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.
Parameterizing 3D Shape Structures with Differentiable Templates for Reconstruction, Generation, and Interpolation
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 形状生成のための微分可能なテンプレートを用いた構造のパラメータ化
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。
3D 모델 생성을 위한 차별화 가능한 템플릿을 이용한 구조 파라미터화: 3D 도면 경계를 활용한 세부 형상 표현 및 효율적인 재구성 및 생성
이 논문에서는 3D 형상의 공유 구조를 학습 가능한 템플릿으로 파라미터화하여 효율적인 3D 형상 생성 및 재구성을 가능하게 하는 새로운 방법을 제안합니다.
© 2024 by Linnk AI