Lists (2)
Stars
Simple model to Track and Re-identify individuals in different cameras/videos.(Yolov3 & Yolov4)
Unreal environments for reinforcement learning
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
A high-performance C++ header and application for real-time metric depth estimation, using models from Depth-Anything-V2. Powered by ONNX Runtime and OpenCV, it supports seamless inference for imag…
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
[ICRA 2025] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail
This repository features the code base for the "Autonomous Drone for Dynamic Smoke Plume Tracking" project.
MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25
[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research
A generative world for general-purpose robotics & embodied AI learning.
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
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 3D Multi Object Tracking using Lidar
Arduinobot is an open-source 3D printed robot arm powered by ROS 2. Its simple design and low cost make it an excellent learning tool, featured in the "Robotics and ROS 2 - Learn by Doing! Manipula…
A cheap educational DIY mobile manipulator - ROS , with instructions on how to build it, starting code and demos
The initiative's importance is to estimate power consumption using time series analysis.
We used Kaggle's Aerial Semantic Segmentation Drone Dataset for this prototype.
This is a simulation project where I used my custom robot, Pathfinder for mapping and autonomous navigation using Robot Operating System (ROS)