AI Agent Skills

AnyLoc: Universal Visual Place Recognition (RA-L 2023)

Robotic actuator test stand utilizing a Capstan Drive reducer

Unofficial PyTorch Reimplementation of RandAugment.

Pytorch implementation of "Fully-Convolutional Siamese Networks for Object Tracking"

[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390 [ECCV 2024]

Build fully-functioning computer vision models with PyTorch

Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning. Pytorch Implementation

This is tensorflow implementation for paper "Deep Image Matting"

[T-PAMI 2025] DiffMVS & CasDiffMVS

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

Dobb·E: An open-source, general framework for learning household robotic manipulation