[CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation

Differentiable wave optics simulation library built on PyTorch

3D Gaussian Splat Editor

[CVPR 2026 Findings] The official code of the paper "Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding".

The ESMStereo models are designed with low computational complexity to achieve an acceptable balance between accuracy and speed, which makes them ideal for real-time stereo matching with exceptiona…

Official repository for the paper "Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance" by Bhattacharya, et al. (2024) from GRASP, Penn.

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Build-your-own DiffuserCam tutorial

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

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

This is a fast and versatile simulator for training vision-based flight of drones.

A procedural Blender pipeline for photorealistic training image generation

Creation of Synthetic Data using Blender, for training A.I. models.

Synthetic Blender Dataset Production

This repo provides tutorials and a library to help CV researchers to generate data using blender.

A simple data generation engine for computer vision, compatible with 🤗 datasets.

Tutorial on pythonically generating Object Detection data in blender

Utilities and supporting library for controlling original Lytro lightfield cameras

Using relativism to improve GAN-based Adversarial Attacks. 🦾

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

A repository for paper "Efficient Solution of Point-Line Absolute Pose" by P.Hruby, T.Duff, and M. Pollefeys, presented at CVPR 2024.

[IROS'24 Oral] A Fully Open-source and Compact Aerial Robot with Omnidirectional Visual Perception

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

AvoidBench

Aerial Gym Simulator - Isaac Gym Simulator for Aerial Robots

Official repo of 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝘀: 𝗪𝗵𝗮𝘁 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄? 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄 𝗧𝗵𝗶𝗻𝗴𝘀? 𝗟𝗲𝘁'𝘀 𝗙𝗶𝗻𝗱 𝗢𝘂𝘁! (Previously titled 𝘐𝘯𝘵𝘳𝘪𝘯𝘴𝘪𝘤 𝘓𝘰𝘙𝘈: 𝘈 𝘎𝘦𝘯𝘦𝘳𝘢𝘭𝘪𝘴𝘵 𝘈𝘱𝘱𝘳𝘰𝘢𝘤𝘩 𝘧𝘰𝘳 𝘋𝘪𝘴𝘤𝘰𝘷𝘦𝘳𝘪𝘯𝘨 𝘒𝘯𝘰𝘸𝘭𝘦𝘥𝘨𝘦 𝘪𝘯 𝘎𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘷𝘦 𝘔𝘰𝘥𝘦𝘭𝘴))

Train a tiny diffusion model even with cpu. Implemented with Pytorch.

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation