2 papers
cs.CV2025
Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation
Fuyou Mao, Beining Wu, Yanfeng Jiang +3
Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion…
cs.GR2024
DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework
Fan Zhang, Naye Ji, Fuxing Gao +9
Speech-driven gesture generation is an emerging domain within virtual human creation, where current methods predominantly utilize Transformer-based architectures that necessitate e…