paper-with-me

Papers

UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion

2024-04-10 · CVPR 2024 1 · Junsheng Zhou, Weiqi Zhang, Baorui Ma, Kanle Shi, Yu-Shen Liu, Zhizhong Han

Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy function. However, they are limited to shapes with closed surfaces, which prevents them from generating diverse 3D real-world contents containing open surfaces. In this work, we present UDiFF, a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally. Our key idea is to generate UDFs in spatial-frequency domain with an optimal wavelet transformation, which produces a compact representation space for UDF generation. Specifically, instead of selecting an appropriate wavelet transformation which requires expensive manual efforts and still leads to large information loss, we propose a data-driven approach to learn the optimal wavelet transformation for UDFs. We evaluate UDiFF to show our advantages by numerical and visual comparisons with the latest methods on widely used benchmarks. Page: https://weiqi-zhang.github.io/UDiFF.

📄 PDF Abstract BibTeX arXiv:2404.06851

Code (1)

qingqingle/mesc-3d pytorch

Tasks

3D Shape GenerationImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes

2024-03-03 · CVPR 2024 1 · Yujie Lu, Long Wan, Nayu Ding, Yulong Wang 외

Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However, common distance field based implicit representations, specifically signed distance field (SDF) for wate…

Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fields

2023-03-01 · Yi He, Haoran Xie, Kazunori Miyata

3D model reconstruction from a single image has achieved great progress with the recent deep generative models. However, the conventional reconstruction approaches with template mesh deformation and implicit fields have …

Model Editing

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

2023-11-28 · Zhengming Yu, Zhiyang Dou, Xiaoxiao Long, Cheng Lin 외

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suf…

3D Reconstruction

FullFormer: Generating Shapes Inside Shapes

2023-03-20 · Tejaswini Medi, Jawad Tayyub, Muhammad Sarmad, Frank Lindseth 외

Implicit generative models have been widely employed to model 3D data and have recently proven to be successful in encoding and generating high-quality 3D shapes. This work builds upon these models and alleviates current…

3D Shape GenerationPoint Cloud Generation

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

2021-11-29 · Benoit Guillard, Federico Stella, Pascal Fua

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces. However, current approaches to converting them into explicit meshes tend to either be expensive or to degrade the accuracy. Here, we exten…