Gangwei XU

pixel-perfect-depth. [NeurIPS 2025] Pixel-Perfect Depth

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

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

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

Stoch-predict-with-Tranformer-LSTM. stock predict with MLP,CNN,RNN,LSTM,Transformer and Transformer-LSTM

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

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

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

BANet. [ICCV 2025] BANet for Mobile Stereo Matching

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

MeFlow. Python

BAT.

ENeRF. Real-time novel view synthesis for dynamic scenes.

PromptDA. Prompt Depth Anything

RAFT-Stereo. Python

RAFT. Python

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

gangweix.github.io. Gangwei's Homepage!