Tiny neural network to detect discrete orientation of text (up,down,left,right)

使用Nanodet+YoloV8-Pose实现指针仪表的实时检测、高精度读数识别（借助ncnn框架）

LightlyTrain is the first PyTorch framework to pretrain computer vision models on unlabeled data for industrial applications

Edit gaussian splatting models

One-shot 3D reconstruction of roof planes from urban satellite images with LOD2

[CVPR 2025] Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes

nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new stan…

Code for "Multi-view Reconstruction via SfM-guided Monocular Depth Estimation". CVPR 2025 (Oral Presentation)

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

Unreal Engine plugin to load (precomputed) OpenStreetMap tiles

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

US building classification using OSM data only

PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View

[ECCV 2024] Consistent 3D Line Mapping

Code from the ECCV 2024 paper "Animal Avatar Reconstructing Animatable 3D Animals from Casual Videos".

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

[ICLR 2024] DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation && [CVPR 2025]DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Parametric completion for polygonal surface reconstruction [CVPR 2025]

Pytorch implementation for "DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes"

[CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation

Code for AutoGeo.