zhenghaohu
Follow
Stars
自由上网、科学上网、魔法上网、网络加速器。免费、公益、性价比、自用机场。 协议有 SS、V2ray、Vless Reality、Trojan、Hysteria、Vmess。 推荐代理软件：Clash系、Singbox系。其他代理软件：小火箭、圈X、Surge、V2ray等
Yuxuan Li, Danfeng Hong, Chenyu Li, Jing Yao, Jocelyn Chanussot. HD-Net: High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition, I…
Collection of Python wheels for Windows (sourced from https://www.lfd.uci.edu/~gohlke/pythonlibs/) Use with python -m pip install --extra-index-url https://pypi.bartbroe.re
[CVPR 2024] 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions
Official Code for the paper ''NL-LinkNet : Toward Lighter but More Accurate Road Extraction with Non-Local Operations" (2019)
Winning algorithms for the SpaceNet 4: Off-Nadir Building Footprint Detection Challenge
About The official implementation of the paper "Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network“. (ECCV 2024)
A multi-stage road extraction method for surface and centerline detection
Road network extraction from satellite imagery, with speed and travel time estimates
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery
Data annotation toolbox supports image, audio and video data.
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Sequential rigid registration and measurement in serial imaging for each contour of an RT Structure set (Elastix, Plastimatch, ffmpeg)
Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)
Monocular Depth Estimation Toolbox based on MMSegmentation.
Official implementation of Adabins: Depth Estimation using adaptive bins
Code of our CVPR2024 paper - DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
Transparent Image Layer Diffusion using Latent Transparency
Techniques for deep learning with satellite & aerial imagery
This is a simple template using HuggingFace Accelerator for DDP-training/Saving/Loading/Pushing.
High-Resolution Image Synthesis with Latent Diffusion Models
[CVPR2024] Official Pytorch Implementation of SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation.
Mora: More like Sora for Generalist Video Generation