Highlights
- Pro
Stars
Code accompanying Bringing Online Egocentric Action Recognition into the wild (RA-L)
[CVPR2025W] Official repository for the paper: "Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation"
Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
Official code releasse for "The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation"
MaskPlanner is a deep learning model for the quick generation of multiple, long-horizon paths from free-form 3D objects represented as point clouds.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Official implementation of "Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives" https://arxiv.org/abs/2502.02487
This repository offers a comprehensive collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-e…
Release repo for our SLAM Handbook
[CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"
List of startups doing AI & ML
[CVPR 2024] PEM: Prototype-based Efficient MaskFormer for Image Segmentation
This is the code repository for the 3D Semantic Novelty Detection via Large-Scale Pre-Trained Models
Official implementation "Egocentric zone-aware action recognition across environments" (Pattern Recognition Letters 2025)
Code for EarthMatch (CVPR 2024 IMW), an iterative coregistration pipeline to localize astronaut photos of Earth
A framework to easily use 32 (and growing) different image matching methods
Official implementation of "A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives", accepted at CVPR 2024.
Interface to stable-baselines3 APIs for training RL policies on gym-registered environments
Slurm experiments launcher for python scripts
Collection of gym environments with support for domain randomization
PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting