This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

PyTorch code and models for the DINOv2 self-supervised learning method.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A General NeRF Acceleration Toolbox in PyTorch.

CLI interfaces & config objects, from types

⭐ Vim for Visual Studio Code

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

aider is AI pair programming in your terminal

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

Seamless operability between C++11 and Python

Minimal solvers for calibrated camera pose estimation

Build and run containers leveraging NVIDIA GPUs

A large scale non-linear optimization library

Factor graphs with Ceres in Python

Vulkan-based implementation of D3D8, 9, 10 and 11 for Linux / Wine

Compatibility tool for Steam Play based on Wine and additional components

Optimise Linux system performance on demand

Sign Agnostic Learning with Derivatives

Implicit Geometric Regularization for Learning Shapes

A generative world for general-purpose robotics & embodied AI learning.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Visual localization made easy with hloc

GLOMAP - Global Structured-from-Motion Revisited