18 papers
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
Chen Zhao, Jiajun Ma, Qilong Huang +6
While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a for…
OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation
Zhaotong Yang, Ying Tai, Jiahui Zhan +3
Unified fashion generation integrates tasks like virtual try-on and garment reconstruction into a single model to reduce task-specific adaptation costs. However, naive parameter sh…
Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training
Hexiao Lu, Xiaokun Sun, Zeyu Cai +4
We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on part-aware optimization, manual as…
Scene Prior Filtering for Depth Super-Resolution
Zhengxue Wang, Zhiqiang Yan, Ming-Hsuan Yang +4
Multi-modal fusion serves as a cornerstone for successful depth map super-resolution. However, commonly used fusion strategies, such as addition and concatenation, fall short of ef…
DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies
Renke Wang, Zhenyu Zhang, Ying Tai +2
Precise human mesh recovery (HMR) from multi-view images remains challenging: end-to-end methods produce entangled errors hard to localize, while fitting-based methods rely on spar…
MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing
Xiaokun Sun, Zeyu Cai, Hao Tang +3
3D morphing remains challenging due to the difficulty of generating semantically consistent and temporally smooth deformations, especially across categories. We present MorphAny3D,…