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 models requires large-scale, high-quality real 3D asset data, whose acquisition remains a long-standing and challenging problem. In this work...
Jiang-Shan Wang, Ze-Qiang Lai, J. Guo et al.· 2 citations
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 provide explicit positional guidance, these models must implicitly infer token positions throughout denoising, limiting their generation qu...
Zi-Juan Ouyang, Ze-Qiang Lai, Jia-Rui Chen et al.· 0 citations
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. However, existing methods can degrade generation quality and fidelity at high sparsity levels. Through controlled oracle comparisons, we trac...
Jia-Rui Chen, Ze-Qiang Lai, Jiang-Shan Wang et al.· 0 citations
ChunkVAE, a sparse grid variational autoencoder organized around local chunks rather than a global latent volume, is introduced, indicating that local compression can scale geometry while retaining the global interface required downstream.
Kaiyi Zhang, Zhihao Liang, Haolin Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
