Auxiliary Loss Reweighting for Image Inpainting
Siqi Hui, Sanping Zhou, Ye Deng, Wenli Huang, Jinjun Wang

TL;DR
This paper introduces a novel adaptive reweighting framework for auxiliary perceptual and style losses in image inpainting, eliminating the need for grid search and improving inpainting quality.
Contribution
The paper proposes Tunable Perceptual and Style Losses along with an Auxiliary Weights Adaptation algorithm for dynamic, efficient loss reweighting during training.
Findings
Improved inpainting results on public datasets.
Elimination of time-consuming grid search for loss weights.
Enhanced performance of state-of-the-art methods.
Abstract
Image Inpainting is a task that aims to fill in missing regions of corrupted images with plausible contents. Recent inpainting methods have introduced perceptual and style losses as auxiliary losses to guide the learning of inpainting generators. Perceptual and style losses help improve the perceptual quality of inpainted results by supervising deep features of generated regions. However, two challenges have emerged with the usage of auxiliary losses: (i) the time-consuming grid search is required to decide weights for perceptual and style losses to properly perform, and (ii) loss terms with different auxiliary abilities are equally weighted by perceptual and style losses. To meet these two challenges, we propose a novel framework that independently weights auxiliary loss terms and adaptively adjusts their weights within a single training process, without a time-consuming grid search.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Image Processing Techniques · Advanced Vision and Imaging
MethodsInpainting
