lok-18/IGNet
ACM MM 2023 | Learning a Graph Neural Network with Cross Modality Interaction for Image Fusion
This project helps improve image analysis by combining details from different types of images, like thermal and standard photos, into a single, clearer picture. It takes in pairs of images from varied sources and outputs a single, enhanced image that retains crucial information from both. Image analysts, surveillance professionals, or medical imaging specialists can use this to get a more comprehensive view.
No commits in the last 6 months.
Use this if you need to merge information from multiple image modalities (e.g., infrared and visible light) into one high-quality, informative image for tasks like object detection or segmentation.
Not ideal if you are looking to process single-channel images without combining them with other modalities, or if your primary need is general image enhancement without multimodal fusion.
Stars
41
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lok-18/IGNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shadow2496/VITON-HD
Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via...
theFoxofSky/ddfnet
The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks
ChristophReich1996/Involution
PyTorch reimplementation of the paper "Involution: Inverting the Inherence of Convolution for...
maryam089/SDViT
Official repository for "Self-Distilled Vision Transformer for Domain Generalization" (ACCV-2022 ORAL)
thomasverelst/dynconv
Code for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (CVPR2020)