Research & Education

HiPER Scientific Calculator is a precise and feature-rich mobile application available for Android and iOS, designed for students, engineers, and anyone who uses math daily. It offers high-precision calculations, symbolic algebra, and the ability to solve equations and inequalities. The app also supports integrals, derivatives, matrices, statistics, and regression analysis. Users can create 2D and 3D graphs, perform unit conversions, and access a wide range of physical and mathematical constants. With over 50 million users worldwide and more than 250,000 five-star ratings, HiPER Scientific Calculator is a trusted tool for complex mathematical tasks, making advanced computations accessible on the go.

NobleAI offers a Science-Based AI and cloud-based VIP Platform designed to accelerate innovation in energy, chemistry, and manufacturing. By embedding scientific laws and domain knowledge into its models, NobleAI generates accurate, interpretable predictions even with limited data. The platform helps companies bring products to market faster, strengthen margins, and optimize product and asset performance, from formulation development to asset optimization. Key features include smart data and model management, insightful predictions, optimized designs, rich visualizations, and explainable AI. It supports diverse industries like energy, consumer packaged goods, and chemicals, enabling faster identification of sustainable alternatives and reducing trial-and-error in R&D.

ESM-Variants is an AI tool designed for visualizing protein mutation scores and analyzing genetic variations. Users can select a protein by its UniProt ID, and the application generates an interactive heatmap displaying mutation scores. A key feature is the ability to optionally overlay ClinVar annotations, providing valuable context for understanding the clinical significance of specific mutations. This tool is particularly useful for researchers and scientists in the field of genomics and proteomics who need to quickly assess and interpret the impact of protein variants. It is hosted on Hugging Face Spaces and is available for free under a CC-BY-NC-4.0 license, making it accessible for academic and non-commercial research.

FocusOnDepth is an AI tool designed for depth estimation in images, hosted as a Hugging Face Space. While the tool aims to provide capabilities for analyzing and processing images to determine depth, it is currently experiencing runtime errors due to insufficient hardware capacity. This makes it unavailable for immediate use. When operational, it would be suitable for researchers and developers interested in image processing and AI model testing, particularly those working with depth perception in computer vision applications. The tool is free to use, making it accessible for experimentation and academic purposes.

2d-gaussian-splatting provides an official implementation for creating geometrically accurate radiance fields using 2D Gaussian Splatting. This open-source project represents scenes with 2D oriented disks and utilizes perspective-correct differentiable rasterization. It includes regularizations to enhance reconstruction quality and offers various meshing approaches for Gaussian splatting, including both bounded and unbounded mesh extraction. The tool supports COLMAP and NeRF Synthetic datasets, and provides scripts for training, rendering, and evaluation of novel view synthesis and geometric reconstruction. It also features integrations with community resources like WebGL/Three.js viewers and offers performance improvements through CUDA operator fusing.

advanced_lane_detection is an open-source project designed for advanced lane detection using computer vision techniques. Developed as part of the Udacity Self-Driving Car Nanodegree, it provides a comprehensive pipeline for identifying lane boundaries in images and video streams. Key steps include camera calibration and distortion correction, creating thresholded binary images using color transforms and gradients, applying perspective transforms for a bird's-eye view, and fitting polynomial curves to detect lane lines. The tool also calculates lane curvature and vehicle position relative to the lane center, and annotates the original image with this information. It's built with Python and relies on libraries like NumPy, OpenCV, Matplotlib, and Pickle.

fpn.pytorch offers a pure PyTorch implementation of the Feature Pyramid Network (FPN) for object detection, building upon the properties of a faster R-CNN implementation. This project stands out for its complete conversion of all NumPy implementations to PyTorch, ensuring a consistent and efficient environment. A key feature is its support for training with batch sizes greater than one, achieved by revising all relevant layers including dataloader, RPN, and ROI-pooling. It also leverages a multiple GPU wrapper (nn.DataParallel) for flexible scaling across one or more GPUs. The implementation integrates three pooling methods—ROI pooling, ROI align, and ROI crop—all adapted for multi-image batch training. Benchmarking has been conducted on datasets like PASCAL VOC and COCO, demonstrating its performance.

IsaacGymEnvs is a collection of reinforcement learning environments specifically designed for the NVIDIA Isaac Gym platform. These environments are optimized for high-performance GPU-based physics simulation, as detailed in the NeurIPS 2021 Datasets and Benchmarks paper. The repository offers an easy-to-use API for creating vectorized environments, supporting various tasks like Ant locomotion, Cartpole, and AllegroHand manipulation. It includes features such as headless training, checkpoint loading, multi-GPU training, population-based training, and integration with Weights & Biases for experiment tracking. The framework also incorporates domain randomization to enhance sim-to-real transfer of trained policies, making it a powerful tool for advanced robot learning research and development.

morphsnakes is an open-source Python library providing an implementation of Morphological Snakes for image segmentation and tracking. This tool is designed for both 2D images and 3D volumes, offering a robust alternative to traditional active contour methods like Geodesic Active Contours or Active Contours without Edges. Unlike these traditional approaches that rely on solving PDEs over floating-point arrays, morphsnakes utilizes morphological operators such as dilation and erosion on binary arrays, leading to faster execution and improved numerical stability. The library includes two main methods: Morphological Geodesic Active Contours (MorphGAC) for images with visible contours requiring preprocessing, and Morphological Active Contours without Edges (MorphACWE) which is more robust to noise and suitable when pixel values of inside and outside regions differ significantly. Installation is straightforward via pip or by directly copying the `morphsnakes.py` file.

SensorsCalibration, also known as OpenCalib, is a comprehensive open-source toolbox designed for multi-sensor calibration in autonomous driving applications. Accurate sensor calibration is a foundational requirement for any autonomous system, enabling precise sensor fusion and subsequent processing steps like obstacle detection, localization, mapping, and control. This toolbox addresses the critical need for reliable calibration of various sensors, including IMU, LiDAR, Camera, and Radar. It offers both road scene-based calibration tools for parameters like camera intrinsics, lidar2imu, and surround-camera, as well as factory calibration tools supporting different board types such as chessboard, circle board, and Apriltag board. Additionally, it includes SensorX2car for online calibration of sensor-to-car coordinate systems.

This open-source project provides a Tensorflow 2.x based implementation of state-of-the-art models for single image super-resolution, including Enhanced Deep Residual Networks (EDSR), Wide Activation for Efficient and Accurate Image Super-Resolution (WDSR), and Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (SRGAN). It offers a high-level training API, enabling users to train models as described in the respective papers and fine-tune EDSR and WDSR models within an SRGAN context. The tool includes a DIV2K data provider for automatic dataset downloads and offers pre-trained weights for quick setup. It's ideal for developers and researchers working on image processing and computer vision tasks.

SphereFace offers a comprehensive open-source implementation of the SphereFace algorithm, a deep hypersphere embedding method for face recognition. This tool provides a full pipeline covering face detection, alignment, and recognition, making it valuable for researchers and developers in computer vision. It includes detailed instructions for installation and usage, demonstrating how to train models on datasets like CASIA-WebFace and evaluate performance on LFW. The repository also features various network architectures, including SphereFace-20, and highlights its state-of-the-art verification performance in challenges like MegaFace. Additionally, it provides insights into the underlying mathematical concepts and practical considerations for training, such as gradient normalization and convergence difficulties, along with links to third-party re-implementations and related angular margin learning resources.

SSL4MIS (Semi Supervised Learning for Medical Image Segmentation) is a comprehensive resource for researchers and developers focusing on medical image analysis. It offers a curated collection of literature reviews and practical code implementations for semi-supervised learning techniques. The repository includes re-implementations of various semi-supervised methods such as Mean Teacher, Entropy Minimization, and FixMatch, adapted for medical image segmentation. Additionally, it supports a range of 2D and 3D backbone networks like UNet, nnUNet, and Swin-UNet. This project aims to establish a benchmark for semi-supervised medical image segmentation, fostering easier evaluation and fair comparison within the medical image computing community. It also covers active learning and source-free domain adaptation for medical image analysis.

synthetic-computer-vision is a GitHub repository dedicated to tracking and organizing resources related to the use of synthetic images in computer vision research. It serves as a valuable hub for researchers, offering a curated list of synthetic datasets such as SunCG, Minos, and Synthia, alongside various tools like AirSim, CARLA, and UnrealCV. The repository also includes a collection of relevant academic publications, categorized by year, with links to papers, code, and project pages. Users are encouraged to contribute by adding missing works or updating existing information through pull requests, making it a collaborative and up-to-date resource for the computer vision community.

Interstellar offers an interactive 3D simulation of a wormhole and a black hole, allowing users to explore these cosmic phenomena. The tool provides various controls, including the ability to adjust speed, field of view, and resolution, enhancing the user's immersive experience. Additionally, a unique teleport feature allows instant travel to the next celestial object within the simulation. Hosted on Hugging Face Spaces, Interstellar is accessible via keyboard, mouse, or touch controls, making it suitable for a wide range of users interested in scientific visualization and exploration. It serves as an engaging platform for educational or exploratory purposes, providing a visual representation of complex astrophysical concepts.

MMAction2 is an open-source toolbox for video understanding built on PyTorch, forming a key part of the OpenMMLab project. It features a modular design, allowing users to easily construct customized video understanding frameworks by combining different components. The toolbox supports five major video understanding tasks: action recognition, action localization, spatio-temporal action detection, skeleton-based action detection, and video retrieval. MMAction2 is well-tested and documented, providing detailed API references and unit tests, making it a robust platform for researchers and developers in the field.

OpenCPU is an open-source system designed for embedded scientific computation and reproducible research using the R programming language. It exposes a simple yet powerful HTTP API for remote procedure calls (RPC) and data interchange with R, offering a reliable and scalable foundation for building statistical services or R-based web applications. The system can run as a single-user development server within an interactive R session or as a multi-user Linux stack based on Apache2. It is fully open source and permissively licensed, providing detailed documentation and example applications for both cloud server and local development installations.

RSL-RL is a GPU-accelerated, lightweight learning library specifically designed for robotics research. It provides a fast and simple implementation of various learning algorithms, including PPO and Student-Teacher Distillation, making it ideal for researchers to quickly prototype and test new ideas without the complexity of larger libraries. The library supports multi-GPU training for high-throughput performance and has been proven effective in numerous research publications. RSL-RL is compatible with popular robot learning environments such as Isaac Lab, Legged Gym, mjlab, and MuJoCo Playground, and can be easily installed via PyPI. Its minimal and readable codebase also offers clear extension points for customization.

SINet is an open-source project for Camouflaged Object Detection (COD), a challenging computer vision task focused on detecting objects that blend into their natural habitat. Developed by Deng-Ping Fan and colleagues, SINet was presented at CVPR 2020 (Oral) and offers a robust baseline for COD research. The repository includes detailed introductions, the Search & Identification Net (SINet) model, and one-key evaluation codes. It also features the COD10K dataset, which provides diverse and meticulously annotated samples for training and testing. SINet is implemented in PyTorch and supports both training and testing, with an enhanced version (SINet-V2) accepted at IEEE TPAMI 2022. The project also highlights potential applications in medical imaging, agriculture, art, and computer vision.

SUSTechPOINTS, hosted on GitHub, provides a comprehensive platform for software development, offering various plans tailored for individuals and organizations. The Free plan includes unlimited public/private repositories, Dependabot security updates, 2,000 CI/CD minutes/month, and 500MB of Packages storage. The Team plan expands on this with access to GitHub Codespaces, repository rules, multiple reviewers in pull requests, and increased CI/CD minutes and package storage. For larger organizations, the Enterprise plan adds advanced security, compliance features like SOC1/SOC2 reports, data residency options, and extensive support, making it suitable for managing complex projects and teams.

This project offers a comprehensive stock market environment built with OpenAI Gym, designed for simulating stock trading strategies using reinforcement learning. It integrates both Deep Q-learning and Policy Gradient algorithms, allowing users to experiment with advanced AI techniques in a financial context. The tool is implemented using Keras and supports various training data, although sample data provided is for Korean stocks. It emphasizes flexibility, encouraging users to modify model architectures and features to develop their own optimized solutions. This makes it an ideal platform for researchers and developers looking to explore and refine AI-driven trading strategies.

splatviz is a comprehensive, open-source Python-based interactive viewer designed for real-time editing and analysis of 3D Gaussian Splatting scenes. Utilizing the pyimgui GUI library, it enables direct manipulation of Gaussian Python objects just before rendering, offering extensive editing and visualization capabilities. Users can view multiple scenes simultaneously, either side-by-side or in a split-screen view, and evaluate Python expressions on the resulting scene. Key features include an Edit Widget for real-time manipulation of Gaussian parameters, an Eval Widget for debugging and visualizing variables, and a Camera Widget with Orbit and WASD modes for flexible scene navigation. It also supports attaching to running 3DGS training sessions for live inspection and editing.

UNeXt-pytorch is the official PyTorch implementation of UNeXt, an MLP-based network specifically designed for rapid medical image segmentation. This tool is ideal for researchers and developers working on medical imaging tasks, particularly those requiring quick processing for point-of-care applications. Based on a MICCAI 2022 paper, it offers a robust and efficient solution for segmenting medical images. The open-source nature of the project, hosted on GitHub, allows for community contributions and flexible integration into existing workflows, providing a strong foundation for advanced medical image analysis.

UniDet is an open-source object detection tool designed to operate across multiple large-scale datasets with an automatically learned unified label space. It was the winning solution of the ECCV 2020 Robust Vision Challenges. The tool offers state-of-the-art performance on datasets such as COCO, Objects365, OpenImages, and Mapillary. A key feature is its ability to predict class labels within this unified space, allowing it to be directly used for testing on novel datasets not included in its training. The repository also provides state-of-the-art baselines for Objects365 and OpenImages. UniDet is built on detectron2, making its inference API familiar to users of that framework.