2 citations · 3 across the 5 of their papers we have counts for
8 papers
Position Forcing: Self-Conditioning 3D Generation
Ziheng Ouyang, Zeqiang Lai, Jiarui Chen +7
Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that…
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. H…
Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?
Jiangshan Wang, Zeqiang Lai, Jiayi Guo +6
Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally believed that training such m…
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Xichen Ye, Yifan Wu, Zhikang Xie +3
Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising s…
PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
Jiangshan Wang, Kang Zhao, Jiayi Guo +5
High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching…
Elastic Diffusion Transformer
Jiangshan Wang, Zeqiang Lai, Jiarui Chen +5
Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and di…
LATTICE: Democratize High-Fidelity 3D Generation at Scale
Zeqiang Lai, Yunfei Zhao, Zibo Zhao +5
We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis…
NaTex: Seamless Texture Generation as Latent Color Diffusion
Zeqiang Lai, Yunfei Zhao, Zibo Zhao +5
We present NaTex, a native texture generation framework that predicts texture color directly in 3D space. In contrast to previous approaches that rely on baking 2D multi-view image…