Sen ZHANG

ekf-imu-depth. [ECCV 2022] Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics

GRPO-for-Llava. GRPO Algorithm for Llava Architecture (Based on Verl)

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

openr. OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Super_MARIO. Python

reward-bench. RewardBench: the first evaluation tool for reward models.

ORL. Python

rlkit. Collection of reinforcement learning algorithms

scope-rl. SCOPE-RL: A python library for offline reinforcement learning, off-policy evaluation, and selection

rl. A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

d3rlpy. An offline deep reinforcement learning library

ReBRAC. Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

ReBRAC. Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

LLaVA-NeXT. Python

flamingo-pytorch. Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

LLaVA-UHD. LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs

xtuner. A Next-Generation Training Engine Built for Ultra-Large MoE Models

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

X2-VLM. All-In-One VLM: Image + Video + Transfer to Other Languages / Domains (TPAMI 2023)

Bunny. A family of lightweight multimodal models.

self-correction-llm-papers. This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

SurgicalPart-SAM. Official implementation of SurgicalPart-SAM (SP-SAM)

Awesome-CV-Foundational-Models.

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

funsearch. Jupyter Notebook

LightZero. [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

SurgicalGym. High-performance GPU-based simulation platform for reinforcement learning with surgical robot learning

DEX. [ICRA 2023] Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

alpha-zero-general. A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

controlgym. Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms

IROS2023PaperList. IROS2023 Paper List

Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions. Solutions of Reinforcement Learning, An Introduction

HyQ. Official code repo for paper: Hybrid RL: Using both offline and online data can make RL efficient.

SurgicalSAM. [AAAI2024] Official implementation of SurgicalSAM

mup. maximal update parametrization (µP)

Awesome-Healthcare-Foundation-Models.

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

Reinforcement-Learning-Papers. Related papers for reinforcement learning, including classic papers and latest papers in top conferences

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

test. Measuring Massive Multitask Language Understanding | ICLR 2021

Prompt4ReasoningPapers. [ACL 2023] Reasoning with Language Model Prompting: A Survey

stable-baselines. A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

PPO. PPO implementation for OpenAI gym environment based on Unity ML Agents

LLMsPracticalGuide. A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

RL4LMs. A modular RL library to fine-tune language models to human preferences

awesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)

llama. Inference code for Llama models

MOSS. An open-source tool-augmented conversational language model from Fudan University

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

RRHF. [NIPS2023] RRHF & Wombat

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

matting-survey. Deep Image Matting: A Comprehensive Survey

VRVO. [ICRA 2022] Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World

InfoOdometry. [IJCV 2022] Information-Theoretic Odometry Learning

DeepSpeedExamples. Example models using DeepSpeed

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Awesome-Deep-Camera-Calibration. Deep Learning for Camera Calibration and Beyond: A Survey

MaskDINO. [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

Deformable-DETR. Deformable DETR: Deformable Transformers for End-to-End Object Detection.

mmtracking. 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.

SiamTrackers. (2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on deep learning

sort. Simple, online, and realtime tracking of multiple objects in a video sequence.

deep_sort. Simple Online Realtime Tracking with a Deep Association Metric

pysot. SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

boxmot. BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

awesome-NeRF-and-3DGS-SLAM. A comprehensive list of Implicit Representations, NeRF and 3D Gaussian Splatting papers relating to SLAM/Robotics domain, including papers, videos, codes, and related websites

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

DVSO. A C++ Implementation of Yang's ECCV 2018 paper DVSO (Deep Virtual Stereo Odometry)

BANet. Source Code for the Paper BA-Net: Dense Bundle Adjustment Network

Event_based_VO-VIO-SLAM. HKU-Dataset for Event-based VO/VIO/SLAM

pytracking. Visual tracking library based on PyTorch.

FreeBook--. 免费书籍，不定期更新

iBook. 收藏一些电子书

rotors_simulator. RotorS is a UAV gazebo simulator

RobustART. The first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitecture design and Training techniques towards diverse noises.

alphatensor. Python

SinNeRF. [ECCV 2022] "SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang

open_vins. An open source platform for visual-inertial navigation research.

MOVEDepth. [AAAI 2023] MOVEDepth: Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning

GBoost2. C++

Boost2_0. Improved version of BOOST algorithm

OptimizeMVS. [CVPR 2019] Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction

idn-solver. ICCV 2021 code release of paper "A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo"

trainable-joint-bilateral-filter-source. This is our implementation of a trainable joint bilateral filter layer (PyTorch)

fastbilateral. Fast Approximation of Bilateral Filter Implementation in Pure Python and Comparison with OpenCV and scikit-image Bilateral Implementations

hdrnet.pytorch. A pytorch re-implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017 https://groups.csail.mit.edu/graphics…

Image-Processing-Joint-Bilateral-Filter. This is an implementation of the Joint Bilateral Filter in python using openCV

TheFastBilateralSolver. Fast bilateral filtering for image processing

bilateral. Bilateral Filter implementation both in Python and C++

BBN. The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

deep_bilateral_network. PyTorch implementation of https://github.com/google/hdrnet for black-box image transformation

bilateralNN. Learning Sparse High Dimensional Filters with Neural Networks

IonQuant. A label free quantification tool.

FragPipe. A cross-platform proteomics data analysis suite

MSFragger. Ultrafast, comprehensive peptide identification for mass spectrometry–based proteomics

rrintcc. A region-region interaction detection tool for case-control studies in GWAS, developed under Linux environment, 2017

facehallucination. Attention-Aware Face Hallucination via Deep Reinforcement Learning, CVPR-17

SPNet. Structure-Preserving Image Super-Resolution via Contextualized Multitask Learning, T-MM 2017.

DDet. Dual-path Dynamic Enhancement Network for RealSR, IEEE SPL 2020

AIM. [IJCAI'21] Deep Automatic Natural Image Matting

RIM. [CVPR 2023] Referring Image Matting

Exploring-Negatives-in-Contrastive-Learning-for-Unpaired-Image-to-Image-Translation. Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation

RealSR-Zero. RealSR-Zero dataset provided by our paper "Criteria Comparative Learning for Real-scene Image Super-Resolution"

particle-sfm. ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

orcidlink-LaTeX-command. LaTeX style file to add a macro for inserting a linked ORCiD logo

Fast-Adaptive-Bilateral-Filtering. Matlab code for "Fast Adaptive Bilateral Filtering", IEEE TIP 2019.

Stereo-Image-SR. A Collection of Algorithms and Datasets for Stereo Image Super-Resolution

hdrnet-pytorch. Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017 https://groups.csail.mit.edu/graphics/hdrnet/

hdrnet. An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

DeepGuidedFilter. Official Implementation of Fast End-to-End Trainable Guided Filter, CVPR 2018

JPerceiver. [ECCV 2022]JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes

P3M. [ACM MM 2021] Privacy-Preserving Portrait Matting

ViTPose. The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

ViTAE-Transformer. The official repo for [NeurIPS'21] "ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias" and [IJCV'22] "ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond"

DUTCode. Pytorch implementation of DUT: Learning Video Stabilization by Simply Watching Unstable Videos

ViTDet. Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object Detection"

HSO. Hybrid Sparse Visual Odometry

FeatDepth. This is the offical codes for the methods described in the "Feature-metric Loss for Self-supervised Learning of Depth and Egomotion".

ot-gan. Code for the paper "Improving GANs Using Optimal Transport"

otdd. Optimal Transport Dataset Distance

STROTSS. Style Transfer by Relaxed Optimal Transport and Self-Similarity (CVPR 2019)

implicit-sinkhorn. Python

robot. code for Fast Point Cloud Registration with Optimal Transport

shapmagn. shape registration

FreeML. A List of Data Science/Machine Learning Resources (Mostly Free)

R-MSFM. Code for R-MSFM

TLIO. Tight Learned Inertial Odometry

binary-tree-visualizer. Visualize binary trees and linked lists using GraphViz, compatible with Leetcode

treevis. Treevis is a small utility to graph LeetCode trees. It's useful to debug visually test cases.

RobotCarDataset-Scraper. Downloads files matching patterns from the Oxford Robotcar Dataset website

OVS_Stabilization.

www.mlcompendium.com. The Machine Learning & Deep Learning Compendium was a list of references in my private & single document, which I curated in order to expand my knowledge, it is now an open knowledge-sharing project compiled using Gitbook.

carla-training-data. Generating training data from the Carla driving simulator in the KITTI dataset format

RAFT. Python

deep_ekf_vio. Python

VINS-Fusion. An optimization-based multi-sensor state estimator

rovio. C++

SharinGAN. Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation"

CVPR21-Deep-Lucas-Kanade-Homography. A generic pipeline to align multimodal image pairs from different sensors by extending Lucas-Kanade on feature maps. CVPR2021

softmax-splatting. an implementation of softmax splatting for differentiable forward warping using PyTorch

stereo-from-mono. [ECCV 2020] Learning stereo from single images using monocular depth estimation networks

LDSO. DSO with SIM(3) pose graph optimization and loop closure

dsm. Direct Sparse Mapping

TrianFlow. Code release for "Towards Better Generalization: Joint Depth-Pose Learning without PoseNet".

cnpy. library to read/write .npy and .npz files in C/C++

stereo_DSO. C++

stereo_dso. C++

stereo_dso. C++

CNN-DSO. Direct Sparse Odometry with CNN Depth Prediction

GASDA. Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation, CVPR 2019

monodepth2. [ICCV 2019] Monocular depth estimation from a single image

SGDepth. [ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

DORN_pytorch. PyTorch implementation of Deep Ordinal Regression Network for Monocular Depth Estimation

AdaBins. Official implementation of Adabins: Depth Estimation using adaptive bins

slamantic. Slamantic

dpc-net. Deep Pose Correction for Visual Localization

demon. DeMoN: Depth and Motion Network

dvo_python. Coding dense visual odometry in a little more than a night (yikes)!

gradslam. gradslam is an open source differentiable dense SLAM library for PyTorch

cube_slam. CubeSLAM: Monocular 3D Object Detection and SLAM

ss-dpc-net. Supporting Code for "Self-Supervised Deep Pose Corrections for Robust Visual Odometry"

tartanvo. TartanVO: A Generalizable Learning-based VO

disk. Disk code release

DSO. dso个人注释版

GFM. [IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

cs676. TeX

awesome-robotics-libraries. :sunglasses: A curated list of robotics libraries and software

awesome-visual-slam. :books: The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

PythonRobotics. Python sample codes and textbook for robotics algorithms.

robotics-coursework. 🤖 Places where you can learn robotics (and stuff like that) online 🤖

MVision. 机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

openvslam. OpenVSLAM: A Versatile Visual SLAM Framework

awesome-slam. A curated list of awesome SLAM tutorials, projects and communities.

DS-SLAM. C++

EmptyCities. Implementation for learning a mapping from images that contain dynamic objects in a city environment to static realistic images

awesome-slam-datasets. A curated list of awesome datasets for SLAM

dso. Direct Sparse Odometry

ORB_SLAM3. ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Convolutional_LSTM_PyTorch. Multi-layer convolutional LSTM with Pytorch

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

distributed_tutorial. Python

transforms3d. 3 dimensional spatial transformations

mav_active_3d_planning. Modular framework for online informative path planning.

UnVIO. The source code of IJCAI2020 paper "Unsupervised Monocular Visual-inertial Odometry Network".

RotationContinuity. Coder for "On the Continuity of Rotation Representations"

all-kinds-crawling-tools. This repository provides all kinds of crawling tools, e.g. image-crawler, paper-crawler

homography-transformation-python. Performs homography transformation between two images, write in python

PRVS-Image-Inpainting. The code for our paper Progressive Reconstruction of Visual Structure for Image Inpainting will be released soon.

SAML. Collect and Select: Semantic Alignment Metric Learning for Few-shot Learning

ServerLoadPred. Server Load Prediction using RNN and dual-stage attention

BAG. Implementation for NAACL-2019 paper

CASe. Implementation for paper " Unsupervised Domain Adaptation on Reading Comprehension "

denoise-imu-gyro. Convolutional Neural Networks for Denoising Gyroscopes of Low-Cost IMUs

SC-SfMLearner-Release. Unsupervised Scale-consistent Depth Learning from Video (IJCV2021 & NeurIPS 2019)

depth_from_video_in_the_wild. SYDE 671 final project source code, copied from Google Research to avoid cloning the entire Google Research repo.