Gangwei XU

[NeurIPS 2025] Pixel-Perfect Depth

[TPAMI 2025 & CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[TPAMI 2024 & CVPR 2022] Attention Concatenation Volume for Accurate and Efficient Stereo Matching

[TPAMI 2024] Fast-ACV: Fast Attention Concatenation Volume for Accurate and Real-time Stereo Matching

[TPAMI 2025 & CVPR 2023] IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching

stock predict with MLP,CNN,RNN,LSTM,Transformer and Transformer-LSTM

A novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability.

Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)

[ICCV 2025] BANet for Mobile Stereo Matching

[ACMMM 2024] Hybrid Cost Volume for Memory-Efficient Optical Flow

No description.

No description.

Real-time novel view synthesis for dynamic scenes.

Prompt Depth Anything

No description.

No description.

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Gangwei's Homepage!

An independent Python feature port of Claude Code, entirely rewritten from scratch. Educational Purpose only.