[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

[ECCV 2024] Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

A free and open-source focus stacking software that supports multi-focus image alignment and fusion.

Official repository for StackMFF-V5.

Source code for AAAI 2026 accepted paper MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

[CVPR 2025 Highlight] UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion

[CVPR 2025 Highlight] UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion

A free and open-source focus stacking software that supports multi-focus image alignment and fusion.

A .NET library that provides access to the library that powers PyTorch.

This is a solution integrating annotation, training, and instance segmentation. It adds a UI based on IntptrMax\YoloSharp, and the UI framework uses MaterialdesignToolkit.

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Train and detect resnet18 with C#

Train Yolo with C#

Official PyTorch implementation of A Defocus and Similarity Attention-Based Cascaded Network for Multi-Focus Misaligned Image Fusion.

Code for “Multi-focus image fusion with visual state space model and dual adversarial learning”

Code for "LightMFF: A Simple and Efficient Ultra-lightweight Multi-focus Image Fusion Network"

Official PyTorch implementation for "StackMFF: end-to-end multi-focus image stack fusion network"

This is a free opensource project for focusstacking images.

Official PyTorch implementation for One-Shot Multi-Focus Image Stack Fusion via Focal Depth Regression

a .NET library that can read/write Office formats without Microsoft Office installed. No COM+, no interop.

[ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepEP: an efficient expert-parallel communication library

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

DeepGEMM: clean and efficient BLAS kernel library on GPU

Injects INotifyPropertyChanged code into properties at compile time

Official repository for the AAAI2025 paper (Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Cod…

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

[IEEE RAL'24 & IROS'24] Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots