A Cone-Constrained Bilinear Decomposition for Total Scaled-Gradient Variation Models

Not specified in the provided content

image restorationvariational methodsoptimizationedge preservation

2609.00036

Builder Relevance

80%

1h ago

Abstract

The paper presents a bilinear decomposition approach to address the computational challenges of the total scaled-gradient variation regularizer in image restoration.

Reality Card

Core Claim

The proposed bilinear decomposition method achieves global convergence and improves image restoration performance, particularly under high noise levels.

Method / Result

Achieves PSNR and SSIM competitive with or superior to representative variational methods, especially at high noise levels.

Limitations

The highly nonconvex and nonlinear nature of the TSGV regularizer may still pose challenges for reproducibility in different contexts.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers