AI Agent Skills

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Code for the paper entitled "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection" (CVPR 2021)

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

[CVPR 2023] Collaborative Diffusion

Pixel-Adaptive Convolutional Neural Networks (CVPR '19)

Official code for CVPR 2022 (Oral) paper "Deep Visual Geo-localization Benchmark"

Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing (CVPR 2024)

[CVPR 2025] Code for Segment Any Motion in Videos

CVPR 2022 HFGI: High-Fidelity GAN Inversion for Image Attribute Editing

[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"

Official implementation of ImageCritic (CVPR 2026)

Pytorch implementation of Structure-Preserving Super Resolution with Gradient Guidance (CVPR 2020 & TPAMI 2021)

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis

[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"