用词典学习实现4D形变体的高效生成，分离形状与运动。
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
- 基于词典学习分离4D形状与运动，用潜空间表示
- 生成高质量4D动画，支持细节保留与结构连续
- 适合需要高保真动态建模的场景，如影视特效
尽管基于扩散模型的3D生成已取得显著进展，但4D生成因物体随时间形变的复杂性仍具挑战。本文提出DNF，一种新的无条件4D生成方法，通过词典学习将4D运动与形状解耦，高效建模可变形形状，并保留高保真细节。形状与运动分别以学习得到的潜空间表示，每个可变形形状由全局潜码、特定形状的系数向量及共享词典信息共同构成，既捕捉形状特异性细节，又保留共享结构信息。该表示在保真度、连续性与压缩率之间取得良好平衡；结合基于Transformer的扩散模型，可生成高质量、连贯的4D动画。
原文摘要 · Abstract (English)
While remarkable success has been achieved through diffusion-based 3D generative models for shapes, 4D generative modeling remains challenging due to the complexity of object deformations over time. We propose DNF, a new 4D representation for unconditional generative modeling that efficiently models deformable shapes with disentangled shape and motion while capturing high-fidelity details in the deforming objects. To achieve this, we propose a dictionary learning approach to disentangle 4D motion from shape as neural fields. Both shape and motion are represented as learned latent spaces, where each deformable shape is represented by its shape and motion global latent codes, shape-specific coefficient vectors, and shared dictionary information. This captures both shape-specific detail and global shared information in the learned dictionary. Our dictionary-based representation well balances fidelity, contiguity and compression -- combined with a transformer-based diffusion model, our method is able to generate effective, high-fidelity 4D animations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。