12 accepted papers
Classifier-Free Guidance (CFG) is a cornerstone of modern text-to-image models, yet its reliance on a semantically vacuous null prompt generates a guidance signal prone to geometric entanglement. This is a key factor limiting its precision, leading to well-documented failures in complex compositiona
We study the problem of minimizing the sum of a smooth function and a nonsmooth convex regularizer over a compact Riemannian submanifold embedded in Euclidean space. By introducing an auxiliary splitting variable, we propose an adaptive Riemannian alternating direction method of multipliers (ARADMM)…
Implicit Neural Representations (INRs) rely heavily on architectural choices for good generalization. Developing theoretically grounded approaches for architecture design remains an active area of research. Via theoretical analysis of the infinite-width limit, we establish a methodology that charact…
Learning pseudo-contractive denoisers is a fundamental challenge in the theoretical analysis of Plug-and-Play (PnP) methods and the Regularization by Denoising (RED) framework. While spectral methods attempt to address this challenge using the power iteration method, they fail to guarantee the trul…
Learning-driven methods have revolutionized the field of blind deconvolution, with SelfDeblur as a pioneering method. It uses deep image priors to jointly estimate blur kernels and latent clear images, employing deep neural networks to automatically learn these priors and effectively capture their s…
Plug-and-Play (PnP) methods are increasingly popular for solving image restoration problems. RED-PRO (regularization by denoising via fixed-point projection) is an important framework that bridges RED and PnP. Balancing the gradient method for data fidelity and the denoiser in RED-PRO with suitable…
Existing video watermarking embeds robust watermarks in each frame of the video for copyright protection and tracking. However, just as any content written on a blank paper is easily perceived, embedding watermarks in the texture-poor frames impairs imperceptibility. Common geometric attacks such as…
The widespread adoption of smartphones has introduced new challenges to document copyright protection, prompting the emergence of Screen-Shooting Resilient Document Watermarking (SSRDW) technology. In recent years, underpainting-based SSRDW techniques have proven to be highly effective. However, aft…
With the rapid development of mobile Internet and video applications, robust video watermarking technology has become a focal area of research for protecting and tracking intellectual property rights in digital media. An important characteristic of video is that it has both spatial and temporal prop…
Noise feature modules are commonly used in image manipulation localization. However, different noise learning modules can only target limited tampering methods. In actual image tampering localization tasks, the tampering methods are unknown; it is difficult for a single noise feature module to match…
Existing image manipulation detection and localization methods tend to detect the trail of manipulation and achieve decent performance. So far, however, there has been little discussion about the category imbalance. In this paper, we propose a parallel attention mechanism based network to localize t…
This paper proposes a regularizer called Implicit Neural Representation Regularizer (INRR) to improve the generalization ability of the Implicit Neural Representation (INR). The INR is a fully connected network that can represent signals with details not restricted by grid resolution. However, its g…