Stars
一个基于可视水印检测识别的数字媒体溯源应用系统，是我的大作业项目，包含这个系统以及一个开源的大规模常见水印图像数据集（Large-scale Common Watermark Dataset, LCWD）。 输入一个带有可视水印的图片或视频，系统会检测定位到水印所在的区域，然后将其提取出来，然后借助百度AI开放平台的OCR和logo识别以及Bing搜索引擎，溯源到这个图片或视频的源头。
AudioMCQ: A 571k audio multiple-choice question dataset for post-training Large Audio Language Models with dual CoT annotations and audio-contribution filtering. 🏆 1st place in DCASE 2025 Challenge.
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
dmitrii-marin / adaptive-sampling
Forked from tensorflow/modelsEfficient Segmentation: Learning Downsampling Near Semantic Boundaries
PyTorch implementation of Learning to Downsample for Segmentation of Ultra-High Resolution Images [ICLR 2022]
OpenMMLab Detection Toolbox and Benchmark
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Reverse Convolution and Its Applications to Image Restoration (ICCV, 2025)
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
Official repository for the AAAI2026 paper (Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach)
Pytorch code for our CVPRw 2023 paper "Cascaded Zoom-in Detector for High Resolution Aerial Images"
ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024)
Official implementation of ICML 2025 Oral 🏆 paper "Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection".
[TGRS] A Lightweight Multistream Framework for Salient Object Detection in Optical Remote Sensing
[CVPR 2025] DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]
[ICCV 2023] GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
Learning Implicit Surfaces from Point Clouds (ECCV 2020)
SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
Official implementation of "RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization"
Reference PyTorch implementation and models for DINOv3
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
OpenMMLab's next-generation platform for general 3D object detection.