Junuk Cha

MultiPerson. Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement

Text2HOI. Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction

DINOv2_pca_visualization. Visualization of the PCA as shown in Figure 1.

DINOv2_classification. Flower classification with DINOv2

SSPSE. Towards Single 2D Image-level Self-supervision for 3D Human Poseand Shape Estimation

cot-pose. Official Code of "CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts" in ICCVW'25

textured_smpl. Python

remove-text. Python

scorenet. Reproduction of Generative Modeling by Estimating Gradients of the Data Distribution

paper_summarization. langchain_llama3