Searcharxiv⌕ Search

arXiv subjects

Yudong Liang

Publications and source records attributed to Yudong Liang.

10 recordsLinked to original sources

ExplicitIR: Explicit Spatial Policy Fields for All-in-One Image Restoration

All-in-one image restoration aims to recover clean images blindly from inputs with various degradation types and levels using a single model. However, the adaptation policy in most existing methods remains implicitly encoded in feature representations, leaving the restoration decision neither explicitly represented nor independently controllable. Since real-world degradations vary spatially, applying uniform updates across the entire image leads to over-smoothing of clean areas and under-correction of localized degradations. To address these limitations, we present ExplicitIR, which represents the restoration policy as two explicit per-pixel fields: Budget, which determines where and how strongly to update, and Style, which selects between narrow and wide context windows. Specifically, ExplicitIR incorporates a Spatial Policy Estimator (SPE) to predict these fields, explicitly representing the restoration policy and capturing spatially-varying degradations, which are then applied by Policy-Adaptive Decoder Blocks (PADB) through adaptive fusion of narrow- and wide-window responses, enabling independent control and precise local modulation. This design enables spatially-adaptive restoration in a single forward pass, without requiring task labels, prompts, or test-time degradation estimators. Extensive experiments on three-task and five-task benchmarks demonstrate that ExplicitIR achieves performance competitive with the strongest all-in-one baselines.

cs.CV↗

A study guide for Bourgain's 2003 sum-product theorem and 2010 discretized projection theorem

These notes present Bourgain's proofs of the discretized sum-product theorem and its applications. The discussion emphasizes the construction of trees with multiscale porosity from small additive doubling, using either quantitative Freiman theorrem or the Plünnecke-Ruzsa inequality, and the amplification of these structures by multiplication. Additive combinatorial tools connect the resulting growth estimates to discretized sum-product problem. The notes also discuss the passage to the exceptional set estimates for orthogonal projections, the exclusion of Borel subrings of intermediate Hausdorff dimension, and Fourier decay for multiplicative convolutions of measures.

math.CA↗

On the proof of Falconer distance conjecture

We are able to catch the main idea from OpenAI's recent release and present a proof of Falconer distance conjecture in our own words. Arguments are judiciously simplified and carefully designed for graduate-level readers.

math.CA↗

Lecture note on Fourier decoupling theory and its applications

This paper is based on lecture notes taken and organized during the 17th Graduate Mathematics Intensive Training Program (Spring 2025), held at the Beijing International Center for Mathematical Research, in which Professor Shaoming Guo lectured on "An Introduction to Fourier Decoupling Theory." The main content includes an introduction to and proofs of $\ell^2$ decoupling inequality, together with its applications in number theory, harmonic analysis, and geometric measure theory. The writing follows Professor Guo's teaching style, proving theorems in an intuitive and heuristic manner; consequently, the text contains many figures to explain the ideas at hand, while also lacking some rigor. However, all of these geometric intuitions can be rigorously justified, albeit in a more complicated and technical way. The author hopes that readers will be able to understand, through these lecture notes, the geometric intuition hidden behind the cumbersome proofs, and thereby deepen their understanding of the relevant definitions and theorems. Rigorous proofs can be found in Professor Guo's forthcoming book, which interested readers may consult.

math.CA↗

Visibility problem in higher dimensions

We show that an almost-everywhere upper bound $b\geq 1$ for the Hausdorff dimension of visible parts of all compact planar sets implies the upper bound $d-2+b$ for visible parts of all compact sets $K$ in $\mathbb{R}^d$, $d\geq3$. Inserting the sharp planar bound $b=3/2$ of Orponen and Rutar \cite{OrponenRutar2026} gives $\dim_H \mathrm{Vis}_e(K)\leq d-1/2$ for almost every $e\in S^{d-1}$. This would answer their Question 1.9 sharply in all dimensions.

math.CA↗

Progressive residual learning for single image dehazing

The recent physical model-free dehazing methods have achieved state-of-the-art performances. However, without the guidance of physical models, the performances degrade rapidly when applied to real scenarios due to the unavailable or insufficient data problems. On the other hand, the physical model-based methods have better interpretability but suffer from multi-objective optimizations of parameters, which may lead to sub-optimal dehazing results. In this paper, a progressive residual learning strategy has been proposed to combine the physical model-free dehazing process with reformulated scattering model-based dehazing operations, which enjoys the merits of dehazing methods in both categories. Specifically, the global atmosphere light and transmission maps are interactively optimized with the aid of accurate residual information and preliminary dehazed restorations from the initial physical model-free dehazing process. The proposed method performs favorably against the state-of-the-art methods on public dehazing benchmarks with better model interpretability and adaptivity for complex hazy data.

eess.IV↗

Progressive Depth Learning for Single Image Dehazing

The formulation of the hazy image is mainly dominated by the reflected lights and ambient airlight. Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase. In turn, the good transmission estimation could facilitate the depth estimation for hazy images. In this paper, a deep end-to-end model that iteratively estimates image depths and transmission maps is proposed to perform an effective depth prediction for hazy images and improve the dehazing performance with the guidance of depth information. The image depth and transmission map are progressively refined to better restore the dehazed image. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas. Extensive results on the benchmarks demonstrate that our proposed network performs favorably against the state-of-the-art dehazing methods in terms of depth estimation and haze removal.

cs.CV↗

Discriminative Feature Learning with Foreground Attention for Person Re-Identification

The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively emphasize the foreground persons becomes very critical to solve the person Re-ID problem. In this paper, we propose a simple yet effective foreground attentive neural network (FANN) to learn a discriminative feature representation for person Re-ID, which can adaptively enhance the positive side of foreground and weaken the negative side of background. Specifically, a novel foreground attentive subnetwork is designed to drive the network's attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons. The resulting feature maps of encoder network are further fed into the body part subnetwork and feature fusion subnetwork to learn discriminative features. Besides, a novel symmetric triplet loss function is introduced to supervise feature learning, in which the intra-class distance is minimized and the inter-class distance is maximized in each triplet unit, simultaneously. Training our FANN in a multi-task learning framework, a discriminative feature representation can be learned to find out the matched reference to each probe among various candidates in the gallery. Extensive experimental results on several public benchmark datasets are evaluated, which have shown clear improvements of our method over the state-of-the-art approaches.

cs.CV↗

Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network

Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numbers of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. In addition, the skip connections have naturally centered the activation which led to better performance. To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed. In particular, a strategy of gradually varying the shape of network has been proposed for residual network. Different residual architectures for image super-resolution have also been compared. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-the-art PSNR and SSIM results for single image super-resolution but also produce visually pleasant results. This paper has extended the mmm 2017 oral conference paper with a considerable new analyses and more experiments especially from the perspective of centering activations and ensemble behaviors of residual network.

cs.CV↗

Single Image Super Resolution - When Model Adaptation Matters

In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors. In this paper we propose a novel deep convolutional neural network carefully designed for robustness and efficiency at both learning and testing. Moreover, we propose a couple of model adaptation strategies to the internal contents of the low resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors we achieve 0.1 up to 0.3dB PSNR improvements over best reported results on standard datasets. Our adaptation especially favors images with repetitive structures or under large resolutions. Moreover, it can be combined with other simple techniques, such as back-projection or enhanced prediction, for further improvements.

cs.CV↗