paper-with-me

Papers

OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching

2022-04-19 · Ostap Viniavskyi, Mariia Dobko, Dmytro Mishkin, Oles Dobosevych

We present OpenGlue: a free open-source framework for image matching, that uses a Graph Neural Network-based matcher inspired by SuperGlue \cite{sarlin20superglue}. We show that including additional geometrical information, such as local feature scale, orientation, and affine geometry, when available (e.g. for SIFT features), significantly improves the performance of the OpenGlue matcher. We study the influence of the various attention mechanisms on accuracy and speed. We also present a simple architectural improvement by combining local descriptors with context-aware descriptors. The code and pretrained OpenGlue models for the different local features are publicly available.

📄 PDF Abstract BibTeX arXiv:2204.08870

Code (1)

ucuapps/openglue 공식 구현 pytorch

Tasks

Graph Neural Network

Similar Papers 제목 키워드 기반

Open-source data pipeline for street-view images: a case study on community mobility during COVID-19 pandemic

2024-01-23 · Matthew Martell, Nick Terry, Ribhu Sengupta, Chris Salazar 외

Street View Images (SVI) are a common source of valuable data for researchers. Researchers have used SVI data for estimating pedestrian volumes, demographic surveillance, and to better understand built and natural enviro…

Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification

2026-02-14 · Daniel Chen, Zaria Zinn, Marcus Lowe arxiv

We introduce GoogleFontsBench, the first public benchmark for classifying open-source web fonts, addressing a gap left by existing benchmarks that cover only commercial typefaces. GoogleFontsBench comprises 394 font vari…

parameter-efficient fine-tuningSynthetic Data Generation

Learning Illumination Control in Diffusion Models

2026-04-27 · Nishit Anand, Manan Suri, Christopher Metzler, Dinesh Manocha 외 arxiv

Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy con…

SMIR: Efficient Synthetic Data Pipeline To Improve Multi-Image Reasoning

2025-01-07 · Andrew Li, Rahul Thapa, Rahul Chalamala, Qingyang Wu 외

Vision-Language Models (VLMs) have shown strong performance in understanding single images, aided by numerous high-quality instruction datasets. However, multi-image reasoning tasks are still under-explored in the open-s…

DescriptiveSynthetic Data Generation

ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework

2026-03-21 · Guanzhou Chen, Erfei Cui, Changyao Tian, Danni Yang 외 arxiv

Instruction-based image editing has emerged as a key capability for unified multimodal models (UMMs), yet constructing large-scale, diverse, and high-quality editing datasets without costly proprietary APIs remains chall…

Image Editing