bw4sz
Follow
Stars
[IJCV 22] An implementation of AutoScale localization-based method
Minimal solvers for calibrated camera pose estimation
A tool for quickly adding labels to unlabeled datasets
A package to read and convert object detection datasets (COCO, YOLO, PascalVOC, LabelMe, CVAT, OpenImage, ...) and evaluate them with COCO and PascalVOC metrics.
A Python package for fast and robust Image Stitching
CVPR 2023 Data Contribution
GEO-Bench: Toward Foundation Models for Earth Monitoring
This paper introduces a forest dataset called FinnWoodlands, which consists of RGB stereo images, point clouds, and sparse depth maps, as well as ground truth manual annotations for semantic, inst…
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Segment Anything in Medical Images
The official codes for the ICCV2021 Oral presentation "Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework"
Official code repository for NeurIPS 2022 paper "SatMAE: Pretraining Transformers for Temporal and Multi-Spectral Satellite Imagery"
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Earth observation tools for Meta AI Segment Anything
KTH Deep Learning advanced (DD2412) project. Task: Reproducing FixMatch and investigating on Noisy (Pseudo) Labels and confirmation Errors of FixMatch.
open-forest-observatory / automate-metashape_archive
Forked from open-forest-observatory/automate-metashape!! NOTE: This copy of the respository was archived on 3 June 2024. Current development is happening at automate-metashape-2 and all users should access the repository there. This archive is being r…
[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
A handy tool for dealing with region of interest (ROI) on the image reconstruction (Metashape & Pix4D) outputs, mainly in agriculture applications
PyTorch implementation of moe, which stands for mixture of experts
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data