SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.04491 · 2021

Improving Image Restoration by Revisiting Global Information Aggregation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Global operations, such as global average pooling, are widely used in top-performance image restorers. They aggregate global information from input features along entire spatial dimensions but behave differently during training and inference in image restoration tasks: they are based on different regions, namely the cropped patches (from images) and the full-resolution images. This paper revisits global information aggregation and finds that the image-based features during inference have a different distribution than the patch-based features during training. This train-test inconsistency negatively impacts the performance of models, which is severely overlooked by previous works. To reduce the inconsistency and improve test-time performance, we propose a simple method called Test-time Local Converter (TLC). Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images. The proposed method can be applied to various global modules (e.g., normalization, channel and spatial attention) with negligible costs. Without the need for any fine-tuning, TLC improves state-of-the-art results on several image restoration tasks, including single-image motion deblurring, video deblurring, defocus deblurring, and image denoising. In particular, with TLC, our Restormer-Local improves the state-of-the-art result in single image deblurring from 32.92 dB to 33.57 dB on GoPro dataset. The code is available at https://github.com/megvii-research/tlc.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2112.04491")
get_code_for_paper("2112.04491")
have("2112.04491")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2112.04491.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2112.04491.svg)](https://syntology.ai/paper/2112.04491)

Connect an agent — have() is free.