Latest

• 3D reconstruction from endoscopy images: A survey
• Free editing of Shape and Texture with Deformable Net for 3D Caricature Generation
• Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer
• DGFormer: Dynamic graph transformer for 3D human pose estimation
• Diffusion model with temporal constraint for 3D human pose estimation
• Foot-constrained Spatial-Temporal Transformer for Keyframe-based Complex Motion Synthesis
• Self-supervised endoscopy depth estimation framework with CLIP-guidance segmentation
• A lightweight pose estimation network with multi-scale receptive field
• KD-Former: Kinematic and dynamic coupled transformer network for 3D human motion prediction
• Neurophysiological and Subjective Analysis of VR Emotion Induction Paradigm
• Human Motion Synthesis and Control via Contextual Manifold Embedding
• EmoDescriptor: A hybrid feature for emotional classification in dance movements
• 3D-CariNet: End-to-end 3D Caricature Generation from Natural Face Images with Differentiable Renderer
• Diverse Dance Synthesis via Keyframes with Transformer Controllers