Image-to-3D generation has become increasingly capable of producing objects that closely resemble the input image, and an outstanding challenge is to reproduce the depicted object itself, including the specific geometry that defines it. Inscriptions, brand marks, and repeated structures are frequently distorted or lost...
Zi-Ying Li, Sheng-Chu Zhao, Hui-Ang He et al.· 0 citations
Hi3D 3.0 is presented, an image-to-3D generation system targeting object-specific fidelity, with Twinkle3D as its geometry model for generating watertight triangle meshes at $2048^{3}$ resolution, with a fine-grained image-3D cross-modal interaction mechanism that strengthens correspondence between visual evidence and...
Zi-Ying Li, Sheng-Chu Zhao, Hui-Ang He et al.· 0 citations
Long-video generation with diffusion transformers (DiTs) produces extremely long token sequences, making attention a dominant inference bottleneck. Dynamic sparse attention reduces computation, but its realized speedup remains limited because irregular query-row execution degrades L2 cache locality and increases HBM tr...
Zi-Jian Dai, Sen-Khoo Han, You-Hui Bai 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.
