🚀💪Maximize your efficiency and productivity. The ultimate hub to manage, customize, and share prompts. (English/中文/Español/العربية). 让生产力加倍的 AI 快捷指令。更高效地管理提示词，在分享社区中发现适用于不同场景的灵感。

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

This is an Arxiv paper collection

A curated list of resources on handling Rolling Shutter effects and Radial Distortions

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

[AAAI 2026] The Official Implementation for "Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation"

HiAD: A General Framework for High-Resolution Anomaly Detection（通用的高分辨率异常检测框架）

OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS

[NeurIPS 2025] Pytorch Implementation for NeurIPS 2025 paper: ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining

[AAAI 2026] 中文公众号报道

[CVPR 2025] UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

[AAAI 2026] AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection

Valeo Anomaly Dataset (VAD)

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Official implementation of the paper "CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection."

[CVPR 2025] Towards Training-free Anomaly Detection with Vision and Language Foundation Models

中文文档：IMU预积分总结与公式推导

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

ROS2 TensorRT Node for Monocular Metric Depth estimation and Point Cloud generation from camera images with Depth Anything V3

LV-DOT: LiDAR-Visual Dynamic Obstacle Detection and Tracking (C++/Python/ROS)

The official implementation of ICCV'25 paper "FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution"

Depth Anything 3

Real-Time Simultaneous Localization and Mapping with LiDAR intensity

Accompanying code for the ICCV2025 paper "MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning"

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2