paper-with-me

Papers

Neural Wavelet-domain Diffusion for 3D Shape Generation

2022-09-19 · Ka-Hei Hui, Ruihui Li, Jingyu Hu, Chi-Wing Fu

This paper presents a new approach for 3D shape generation, enabling direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets, and formulate a pair of neural networks: a generator based on the diffusion model to produce diverse shapes in the form of coarse coefficient volumes; and a detail predictor to further produce compatible detail coefficient volumes for enriching the generated shapes with fine structures and details. Both quantitative and qualitative experimental results manifest the superiority of our approach in generating diverse and high-quality shapes with complex topology and structures, clean surfaces, and fine details, exceeding the 3D generation capabilities of the state-of-the-art models.

📄 PDF Abstract BibTeX arXiv:2209.08725

Code (1)

edward1997104/Wavelet-Generation 공식 구현 pytorch

Tasks

3D Generation3D Shape 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

Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation

2023-02-01 · Jingyu Hu, Ka-Hei Hui, Zhengzhe Liu, Ruihui Li 외

This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact …

3D Shape Generation

UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion

2024-04-10 · CVPR 2024 1 · Junsheng Zhou, Weiqi Zhang, Baorui Ma, Kanle Shi 외

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 an…

3D Shape GenerationImage Generation

3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes

2024-11-28 · Tejaswini Medi, Arianna Rampini, Pradyumna Reddy, Pradeep Kumar Jayaraman 외

Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike diffusion models, AR models enable more …

3D Shape ModelingImage Generation

Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion

2024-11-21 · Jinhong He, Shivakumara Palaiahnakote, Aoxiang Ning, Minglong Xue

Due to the singularity of real-world paired datasets and the complexity of low-light environments, this leads to supervised methods lacking a degree of scene generalisation. Meanwhile, limited by poor lighting and conten…

Image EnhancementImage GenerationLow-Light Image Enhancement

WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation

2025-10-13 · Yu-Hsiang Wang, Olgica Milenkovic arxiv

Time series are ubiquitous in many applications that involve forecasting, classification and causal inference tasks, such as healthcare, finance, audio signal processing and climate sciences. Still, large, high-quality t…

Causal Inference