[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

Kernel Point Convolution implemented in PyTorch

📊 Benchmark multiple object trackers (MOT) in Python

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]

📚 计算机经典编程书籍、大黑书、编程电子书、电子书、编程书籍，包括计算机基础、C/C++、Java、Python、面试题、架构设计、算法系列等经典电子书。

Single-header C++ HTTP request class

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

I am not sure this was the final version for training the wave encoder and decoder that I used for the paper, but this is what I can find for now.

Official Pytorch Implementation for "Splicing ViT Features for Semantic Appearance Transfer" presenting "Splice" (CVPR 2022 Oral)

Software that can perform photorealistic style transfer without the need of any post-processing steps.

Pure Pytorch Docker Images.

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

[F2DNet] Fast Focal Detection Network for Pedestrian Detection

Deep Reinforcement Learning

Joint Detection and Embedding for fast multi-object tracking

Pytorch framework for doing deep learning on point clouds.

Python scripts to generate the synthetic data for Paris-CARLA-3D dataset

Zhejiang University Graduation Thesis LaTeX Template

[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.