Stars
🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.
About code release of "Transolver: A Fast Transformer Solver for PDEs on General Geometries", ICML 2024 Spotlight. https://arxiv.org/abs/2402.02366
TorchCFM: a Conditional Flow Matching library
[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Installer & Activited Microsoft Office For MacOS
[CVPR 2024] WaveMo: Learning Wavefront Modulations to See Through Scattering
[arXiv] PyTorch implementation of "The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D Knowledge".
Real-time physical light transport (PLT) framework
程序员延寿指南 | A programmer's guide to live longer
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
Official code for Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM
Official implementation of "E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models"
Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. M 8053 euleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025
UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
Code release for paper "Test-Time Training Done Right"
Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Implementation of the paper Gaussian Fluids: A Grid-Free Fluid Solver based on Gaussian Spatial Representation
Peking University Undergraduate Thesis Template.
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis