Stars
A rewrite of the old legacy software "depends.exe" in C# for Windows devs to troubleshoot dll load dependencies issues.
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
[ICCV 2019] Monocular depth estimation from a single image
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
3DGS Render by KIRI Engine
4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.
基于 [awesome-ai-research-writing](https://github.com/Leey21/awesome-ai-research-writing) 的 Web 界面，提供论文写作辅助功能。
Apollo is a reliable configuration management system suitable for microservice configuration management scenarios.
Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.
ComfyUI support for DepthAnything V3 model
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A technical report on convolution arithmetic in the context of deep learning
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Light fields, wide-baseline, sparse, depth estimation, disparity estimation
「3D视觉(三维重建、SLAM、AR/VR) + 传统图像处理 + 计算机视觉(偏AI) 」重要知识点和面试问题。
A Multi-sensor SLAM Dataset Focusing on Corner Cases for Ground Robots (ROBIO2023)
[ICLR 2026] Streaming 4D Visual Geometry Transformer
Open source code for AlphaFold 2.