- * StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows [paper] [code]
- * ClothCap: Seamless 4D Clothing Capture and Retargeting [TOG 2021] [paper]
- Disentangled Image Generation Through Structured Noise Injection [paper]
- * Unsupervised Learning of Object Landmarks through Conditional Image Generation[paper] [code1] [code2]
- * Unsupervised Discovery of Object Landmarks as Structural Representations [paper][code]
- * UNSUPERVISED DISCOVERY OF PARTS, STRUCTURE, AND DYNAMICS [paper] [code]
- Synthesizing Images of Humans in Unseen Poses [paper] [code]
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks [paper] [code]
- TRB: A Novel Triplet Representation for Understanding 2D Human Body [paper] [code]
- Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network [paper] [code]
- BODY-STRUCTURE BASED FEATURE REPRESENTATION FOR PERSON RE-IDENTIFICATION [paper] [code]
- Structured feature learning for pose estimation [paper] [code]
- Hierarchical Human Representation and Data Synthesis [paper] [code]
- Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing [paper] [code]
- * Walk Like A Supermodel: Fashion Generation with Pose Adaptation [paper]
- * First Order Motion Model for Image Animation [paper] [code]
- * Animating Arbitrary Objects via Deep Motion Transfer [paper] [code]
- * Learning Character-Agnostic Motion for Motion Retargeting in 2D [paper] [code]
- * Joint discriminative and generative learning for person re-identification [paper] [code]
- robotics