Lists (31)
3D重建
3D相关1 repository
AIGC
11 repositories
BNN、BCNN、加速
加速5 repositories
C++
6 repositories
deepstream
deepstream 相关4 repositories
Denoising
Denoising,去噪,4 repositories
Image_Enhance
图像增强、去噪、去模糊、去雾、去雨等8 repositories
LLIE
Low Light Image Enhancement15 repositories
NLP
NLP相关8 repositories
OCR
6 repositories
sam相关
sam大模型相关2 repositories
人脸检测
5 repositories
修复
9 repositories
去雾
去雾12 repositories
图像超分
15 repositories
大模型
32 repositories
待复现项目
觉得OK，感觉可以复现的项目仓26 repositories
扩散模型Diffusion_models
生成模型22 repositories
数据集
数据集5 repositories
有意思的网络
11 repositories
有趣的代码
58 repositories
活体检测
1 repository
测距，深度估计
3 repositories
画模型图
2 repositories
目标识别、目标跟踪
目标识别、目标跟踪36 repositories
船舶检测
2 repositories
训练及部署相关
5 repositories
论文列表
CVPR 集合等1 repository
语音识别
1 repository
车道线识别
9 repositories
面试
7 repositories
Starred repositories
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Master programming by recreating your favorite technologies from scratch.
Python decompiler for modern Python versions.
Around View Monitor Algorithm Pipeline
[AAAI26 Oral] "SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection" and [Arxiv 26] "Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining"
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
Curated coding interview preparation materials for busy software engineers
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
This repo is the official implementation of "Robust Maritime Object Detection under Adverse Conditions via Joint Semantic Learning without Extra Computational Overhead", IROS 2025.
[TITS 2023] Dataset-Asynchronous Trajectory Matching-based Multimodal Maritime Data Fusion for Vessel Traffic Surveillance in Inland Waterways
Hold necessary code for our organized denoising challenge associated to ICCV 2025
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
[DEIMv2] Real Time Object Detection Meets DINOv3
Next-generation Albumentations: dual-licensed for open-source and commercial use
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Enjoy the magic of Diffusion models!
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Taming Transformers for High-Resolution Image Synthesis
Inpaint anything using Segment Anything and inpainting models.