Few-step autoregressive video diffusion enables efficient generation, yet maintaining consistency over long rollouts remains challenging, especially when subjects or scenes reappear after going out of sight. Despite progress in fidelity and rollout robustness, existing distillation methods do not fully exploit richer h...
Hang-Yi Kuang, Cheng-Zhi Wang, Ye-Fei He et al.· 0 citations
A proposed taxonomy organizes the research directions into five key problems that drive recent research development: feature enhancement, geometry awareness, model efficiency, augmentation strategies and temporal-aware models, and outlines future directions to address open challenges such as scalability, evaluation sta...
This work proposes a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism, and presents OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs.
Jin Li, Tao Chen, Kai-Ao Wen et al.· arXiv.org· 2 citations· ⚡1
Leveraging the paradigm of autoregressive diffusion, text-conditioned interactive video world models aim to simulate temporally coherent environments guided by textual instructions. While enabling low-latency, long-duration generation is pivotal for embodied AI and simulation-based planning, current frameworks primaril...
Ze-Yu Zhang, Jin-Yuan Mao, Da-Kai An et al.· arXiv.org· 0 citations
Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed-size sets of global tokens, both suffering sharp reconstruction degradation when compressed to extremely low token budgets. In this paper,...
Mingda Lin, Weijie Wang, Zeyu Zhang et al.· 0 citations
Block3D is proposed, a block-wise diffusion framework that partitions the discrete shape-token sequence into contiguous blocks, generates the blocks autoregressively, and jointly denoises all tokens within the current block and introduces confidence-guided intra-block correction, which revises low-confidence tokens bef...
Bowen Cui, Weijie Wang, Zeyu Zhang et al.· 1 citation
BiVidGen, a hybrid framework where an MLLM first generates semantic visual tokens and a DiT renders videos conditioned on both text and these tokens via multi-layer cross-attention is proposed.
Yan-Bo Ding, Yijia Fan, Caihua Shan 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.
