6 papers
Image Diffusion Models Are Good 3D Human Motion Generators
Siyuan Yang, Chong Wang, Hao Cheng +4
Text-to-motion generation typically relies on dataset-specific skeletal representations, with models trained separately for benchmarks with different joint layouts. We investigate…
TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons
Qichen Zheng, Siyuan Yang, Chong Wang +4
Text-driven motion editing modifies an existing motion sequence according to a text instruction while preserving the content of the source motion. Existing methods are typically bu…
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
Chong Wang, Zixuan Fu, Shiqi Huang +3
Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform refinement across depth. Natu…
Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models
Siyuan Yang, Jun Liu, Hao Cheng +5
Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal sce…
Adaptive Decision Boundary for Few-Shot Class-Incremental Learning
Linhao Li, Yongzhang Tan, Siyuan Yang +3
Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from a limited set of training samples without forgetting knowledge of previously learned classes…
Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual
Chong Wang, Lanqing Guo, Zixuan Fu +4
Plug-and-play (PnP) methods offer an iterative strategy for solving image restoration (IR) problems in a zero-shot manner, using a learned \textit{discriminative denoiser} as the i…