arXiv subjects

Fangzhou Luo

Publications and source records attributed to Fangzhou Luo.

6 recordsLinked to original sources

arXiv2026

Subcritical limits of a 1D KPZ growth surface with finite moments

We consider the one-dimensional random growth surface introduced by Adhikari and Chatterjee [AC24], where the height function is defined recursively via the heights at two neighboring sites and an independent noise term at each space-time point. In the subcritical regime, assuming uniformly bounded eighth moments of the noise variables and appropriate regularity of the driving function, we establish convergence in law of the suitably rescaled height function to the solution of the additive stochastic heat equation. Our approach employs a direct recursive renormalization scheme. A central component is a graph representation of the renormalization terms, which enables the derivation of the high-moment bounds essential to the renormalization procedure.

math.PR↗

arXiv2025

Rare event probabilities in Random Geometric Graphs

In this paper, we study rare events in spherical and Gaussian random geometric graphs in high dimensions. In these models, the vertices correspond to points sampled uniformly at random on the $d$ dimensional unit sphere or correspond to $d$ dimensional standard Gaussian vectors, and edges are added between two vertices if the inner-product between their corresponding points are greater than a threshold $t_p$, chosen such that the probability of having an edge is equal to $p$. We focus on two problems: (a) the probability that the RGG is a complete graph, and (b) the probability of observing an atypically large number of edges. We obtain asymptotically exponential decay rates depending on $n$ and $d$ of the probabilities of these rare events through a combination of geometric and probabilistic arguments.

math.PR↗

arXiv2025

NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results

This paper presents an overview of the NTIRE 2025 Challenge on UGC Video Enhancement. The challenge constructed a set of 150 user-generated content videos without reference ground truth, which suffer from real-world degradations such as noise, blur, faded colors, compression artifacts, etc. The goal of the participants was to develop an algorithm capable of improving the visual quality of such videos. Given the widespread use of UGC on short-form video platforms, this task holds substantial practical importance. The evaluation was based on subjective quality assessment in crowdsourcing, obtaining votes from over 8000 assessors. The challenge attracted more than 25 teams submitting solutions, 7 of which passed the final phase with source code verification. The outcomes may provide insights into the state-of-the-art in UGC video enhancement and highlight emerging trends and effective strategies in this evolving research area. All data, including the processed videos and subjective comparison votes and scores, is made publicly available at https://github.com/msu-video-group/NTIRE25_UGC_Video_Enhancement.

cs.CV↗

arXiv2024

Learning Degradation-Independent Representations for Camera ISP Pipelines

Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images. However, ISP-generated images usually suffer from imperfections due to the compounded degradations that stem from sensor noises, demosaicing noises, compression artifacts, and possibly adverse effects of erroneous ISP hyperparameter settings such as ISO and gamma values. In a general sense, these ISP imperfections can be considered as degradations. The highly complex mechanisms of ISP degradations, some of which are even unknown, pose great challenges to the generalization capability of deep neural networks (DNN) for image restoration and to their adaptability to downstream tasks. To tackle the issues, we propose a novel DNN approach to learn degradation-independent representations (DiR) through the refinement of a self-supervised learned baseline representation. The proposed DiR learning technique has remarkable domain generalization capability and consequently, it outperforms state-of-the-art methods across various downstream tasks, including blind image restoration, object detection, and instance segmentation, as verified in our experiments.

cs.CV↗

arXiv2023

Self-Supervised Face Image Restoration with a One-Shot Reference

For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). By explicitly modeling semantics information from a given reference image, SAIR is able to reliably restore severely degraded images not only to high-resolution and highly realistic looks but also to correct semantics. Quantitative and qualitative experiments collectively demonstrate the superior performance of the proposed SAIR. Our code is available at https://github.com/Liamkuo/SAIR.

cs.CV↗

arXiv2021

Functional Neural Networks for Parametric Image Restoration Problems

Almost every single image restoration problem has a closely related parameter, such as the scale factor in super-resolution, the noise level in image denoising, and the quality factor in JPEG deblocking. Although recent studies on image restoration problems have achieved great success due to the development of deep neural networks, they handle the parameter involved in an unsophisticated way. Most previous researchers either treat problems with different parameter levels as independent tasks, and train a specific model for each parameter level; or simply ignore the parameter, and train a single model for all parameter levels. The two popular approaches have their own shortcomings. The former is inefficient in computing and the latter is ineffective in performance. In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model. Unlike a plain neural network, the smallest conceptual element of our FuncNet is no longer a floating-point variable, but a function of the parameter of the problem. This feature makes it both efficient and effective for a parametric problem. We apply FuncNet to super-resolution, image denoising, and JPEG deblocking. The experimental results show the superiority of our FuncNet on all three parametric image restoration tasks over the state of the arts.

eess.IV↗