All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Fast Segment Anything

Next-Token Prediction is All You Need

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

AI-powered arXiv research assistant prototype.

PyTorch code for "SOLAR: Second-Order Loss and Attention for Image Retrieval". In ECCV 2020

A PyTorch re-implementation of Neural Radiance Fields

[ICCV 2019] Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

[ICCVw19] DAME WEB: DynAmic MEan with Whitening Ensemble Binarization for Landmark Retrieval without Human Annotation

My personal note about local and global descriptor

Toolkit for the BOP benchmark, including evaluation scripts and utilities for 6D object pose estimation and related tasks.

Code for the TCAV ML interpretability project

Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]

The following code Vaporwaves an image

Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering

A brief computer graphics / rendering course

Differentiable rendering without approximation.

2-Line Exhaustive Searching for Real-Time Vanishing Point Estimation in Manhattan World

Implementation of PoseNet using pytorch

21st century AD

High Fidelity Simulator for Reinforcement Learning and Robotics Research.

🐍 Geometric Computer Vision Library for Spatial AI

Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

My configuration

NYU Deep Learning Spring 2020

A resource repository for 3D machine learning

A library for efficient similarity search and clustering of dense vectors.

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow