arXiv subjects

Yuanlin Zhang

Publications and source records attributed to Yuanlin Zhang.

At least 19 recordsLinked to original sources

arXiv2026

3D-USE: From Image-Level to Scene-Level Underwater Enhancement

Underwater 3D reconstruction faithfully reproduces the color shifts and visibility loss of captured views, while physical inversion may leave estimation errors in the recovered scene appearance. We formulate Underwater Scene-level Enhancement (USE) as learning a persistent, visibility-enhanced 3D scene representation from degraded multi-view underwater observations, enabling consistent enhanced rendering. Realizing USE requires both a reliable scene representation for enhancement and a consistent enhancement target without paired enhanced 3D data. Therefore, we present 3D-USE, a two-stage framework. First, the Medium Radial Basis Anchor Representation (MediumRBF) establishes a medium-aware Gaussian scene by representing water effects with shared radial-basis anchors and explicitly decomposing object and medium contributions. Based on this fixed scene representation, Appearance Transition Consensus (ATC) transfers paired 2D underwater image enhancement (UIE) knowledge into scene-global and Gaussian-local targets, avoiding direct supervision from inconsistent enhanced views. An Underwater Bilateral Appearance Field (U-BAF) then realizes these targets in Gaussian radiance and medium appearance. The scene directly renders enhanced novel views without a 2D UIE model at inference. Experiments on real underwater scenes show improved visibility and cross-view consistency while preserving reconstruction quality.

cs.CV↗

arXiv2026

3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling

Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and absorption in water body bring inhomogeneous medium attenuation interference that disrupts conventional volume rendering assumptions of uniform propagation medium. While 3D Gaussian Splatting (3DGS) offers real-time rendering capabilities, it struggles with underwater inhomogeneous environments where scattering media introduces artifacts and inconsistent appearance. In this study, we propose a physics-based framework that disentangles object appearance from water medium effects through tailored Gaussian modeling. Our approach introduces appearance embeddings, which are explicit medium representations for backscatter and attenuation, enhancing scene consistency. In addition, we propose a depth-guided optimization strategy that leverages pseudo-depth maps as supervision with depth regularization and scale penalty terms to improve geometric fidelity. By integrating the proposed appearance and medium modeling components via an underwater imaging model, our approach achieves both high-quality novel view synthesis and physically accurate scene restoration. Experiments demonstrate our significant improvements in rendering quality and restoration accuracy over existing methods. The project page is available at https://bilityniu.github.io/3D-UIR.

cs.CV↗

arXiv2026

MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation

Semantic watermarks exhibit strong robustness against conventional image-space attacks. In this work, we show that such robustness does not survive under micro-geometric perturbations: spatial displacements can remove watermarks by breaking the phase alignment. Motivated by this observation, we introduce MarkCleaner, a watermark removal framework that avoids semantic drift caused by regeneration-based watermark removal. Specifically, MarkCleaner is trained with micro-geometry-perturbed supervision, which encourages the model to separate semantic content from strict spatial alignment and enables robust reconstruction under subtle geometric displacements. The framework adopts a mask-guided encoder that learns explicit spatial representations and a 2D Gaussian Splatting-based decoder that explicitly parameterizes geometric perturbations while preserving semantic content. Extensive experiments demonstrate that MarkCleaner achieves superior performance in both watermark removal effectiveness and visual fidelity, while enabling efficient real-time inference. Our code will be made available upon acceptance.

eess.IV↗

arXiv2025

From Research to Resources: Assessing Student Understanding and Skills in Quantum Computing

The revolutionary new field of Quantum Computing (QC) continues to gain attention in industry, academia, and government in both research and education. At educational institutions, there is a proliferation of introductory courses at various academic levels signaling a growing interest and recognition of the significance of this field. A crucial and often overlooked aspect is the development of research-based materials and pedagogical approaches to effectively teach the complexities of quantum computing to diverse cohorts of learners across multiple disciplines. There is a great need for empirical investigations of the effectiveness of learning materials and pedagogical approaches in this new interdisciplinary field. We present an empirical investigation done at an R1 institution using the multiple case study method. We compare a case study on students in an introductory QC course without research-based mini-tutorials to a study of students taking the QC course with research-based mini-tutorials. We compare the strengths and difficulties of students in the two courses, discuss the general strengths and difficulties of students across both courses, postulate the effectiveness of the mini-tutorials and discuss how they can be revised. Strengths across both classes include the ability to apply single-qubit and two-qubit gates, favoring application of Dirac notation, and a reasonable understanding of normalization, probability and teleportation described qualitatively. Difficulties across both classes included use of matrix representation, use of rotation gates, and an ability to recall and analyze quantitatively a circuit representing teleportation.

physics.ed-ph↗

arXiv2023

Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework

In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied simultaneously to improve the decision-making performance of the agent. Firstly, the actions of the agent are divided into high quality actions and low quality actions according to the rewards returned from the environment. Then, the director network is trained to have the ability to discriminate high and low quality actions and guide the actor network to reduce the repetitive exploration of low quality actions in the early stage of training. In addition, we propose an improved double estimator method to better solve the problem of overestimation in the field of reinforcement learning. For the two critic networks used, we design two target critic networks for each critic network instead of one. In this way, the target value of each critic network can be calculated by taking the average of the outputs of the two target critic networks, which is more stable and accurate than using only one target critic network to obtain the target value. In order to verify the performance of the actor-director-critic framework and the improved double estimator method, we applied them to the TD3 algorithm to improve the TD3 algorithm. Then, we carried out experiments in multiple environments in MuJoCo and compared the experimental data before and after the algorithm improvement. The final experimental results show that the improved algorithm can achieve faster convergence speed and higher total return.

cs.LG↗

arXiv2022

A Preliminary Data-driven Analysis of Common Errors Encountered by Novice SPARC Programmers

Answer Set Programming (ASP), a modern development of Logic Programming, enables a natural integration of Computing with STEM subjects. This integration addresses a widely acknowledged challenge in K-12 education, and early empirical results on ASP-based integration are promising. Although ASP is considered a simple language when compared with imperative programming languages, programming errors can still be a significant barrier for students. This is particularly true for K-12 students who are novice users of ASP. Categorizing errors and measuring their difficulty has yielded insights into imperative languages like Java. However, little is known about the types and difficulty of errors encountered by K-12 students using ASP. To address this, we collected high school student programs submitted during a 4-session seminar teaching an ASP language known as SPARC. From error messages in this dataset, we identify a collection of error classes, and measure how frequently each class occurs and how difficult it is to resolve.

cs.CY↗

arXiv2021

MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening

Dominant pan-sharpening frameworks simply concatenate the MS stream and the PAN stream once at a specific level. This way of fusion neglects the multi-level spectral-spatial correlation between the two streams, which is vital to improving the fusion performance. In consideration of this, we propose a Multi-level and Enhanced Spectral-Spatial Fusion Network (MESSFN) with the following innovations: First, to fully exploit and strengthen the above correlation, a Hierarchical Multi-level Fusion Architecture (HMFA) is carefully designed. A novel Spectral-Spatial (SS) stream is established to hierarchically derive and fuse the multi-level prior spectral and spatial expertise from the MS stream and the PAN stream. This helps the SS stream master a joint spectral-spatial representation in the hierarchical network for better modeling the fusion relationship. Second, to provide superior expertise, consequently, based on the intrinsic characteristics of the MS image and the PAN image, two feature extraction blocks are specially developed. In the MS stream, a Residual Spectral Attention Block (RSAB) is proposed to mine the potential spectral correlations between different spectra of the MS image through adjacent cross-spectrum interaction. While in the PAN stream, a Residual Multi-scale Spatial Attention Block (RMSAB) is proposed to capture multi-scale information and reconstruct precise high-frequency details from the PAN image through an improved spatial attention-based inception structure. The spectral and spatial feature representations are enhanced. Extensive experiments on two datasets demonstrate that the proposed network is competitive with or better than state-of-the-art methods. Our code can be found in github.

cs.CV↗

arXiv2020

Google Trends Analysis of COVID-19

The World Health Organization (WHO) announced that COVID-19 was a pandemic disease on the 11th of March as there were 118K cases in several countries and territories. Numerous researchers worked on forecasting the number of confirmed cases since anticipating the growth of the cases helps governments adopting knotty decisions to ease the lockdowns orders for their countries. These orders help several people who have lost their jobs and support gravely impacted businesses. Our research aims to investigate the relation between Google search trends and the spreading of the novel coronavirus (COVID-19) over countries worldwide, to predict the number of cases. We perform a correlation analysis on the keywords of the related Google search trends according to the number of confirmed cases reported by the WHO. After that, we applied several machine learning techniques (Multiple Linear Regression, Non-negative Integer Regression, Deep Neural Network), to forecast the number of confirmed cases globally based on historical data as well as the hybrid data (Google search trends). Our results show that Google search trends are highly associated with the number of reported confirmed cases, where the Deep Learning approach outperforms other forecasting techniques. We believe that it is not only a promising approach for forecasting the confirmed cases of COVID-19, but also for similar forecasting problems that are associated with the related Google trends.

cs.LG↗

arXiv2018

onlineSPARC: a Programming Environment for Answer Set Programming

Recent progress in logic programming (e.g., the development of the Answer Set Programming paradigm) has made it possible to teach it to general undergraduate and even middle/high school students. Given the limited exposure of these students to computer science, the complexity of downloading, installing and using tools for writing logic programs could be a major barrier for logic programming to reach a much wider audience. We developed onlineSPARC, an online answer set programming environment with a self contained file system and a simple interface. It allows users to type/edit logic programs and perform several tasks over programs, including asking a query to a program, getting the answer sets of a program, and producing a drawing/animation based on the answer sets of a program.

cs.AI↗

arXiv2018

Vicious Circle Principle and Logic Programs with Aggregates

The paper presents a knowledge representation language $\mathcal{A}log$ which extends ASP with aggregates. The goal is to have a language based on simple syntax and clear intuitive and mathematical semantics. We give some properties of $\mathcal{A}log$, an algorithm for computing its answer sets, and comparison with other approaches.

cs.AI↗

arXiv2018

Introducing Computer Science to High School Students through Logic Programming

This paper investigates how high school students in an introductory computer science course approach computing in the Logic Programming (LP) paradigm. This qualitative study shows how novice students operate within the LP paradigm while engaging in foundational computing concepts and skills: students are engaged in a cyclical process of abstraction, reasoning, and creating representations of their ideas in code while also being informed by the (procedural) requirements and the revision/debugging process. As these computing concepts and skills are also expected in traditional approaches to introductory K-12 CS courses, this paper asserts that LP is a viable paradigm choice for high school novices. This paper is under consideration in Theory and Practice of Logic Programming (TPLP).

cs.CY↗

arXiv2017

Logic Programming for an Introductory Computer Science Course for High School Students

This paper investigates how high school students approach computing through an introductory computer science course situated in the Logic Programming (LP) paradigm. This study shows how novice students operate within the LP paradigm while engaging in foundational computing concepts and skills, and presents a case for LP as a viable paradigm choice for introductory CS courses.

cs.CY↗

arXiv2017

An Online Development Environment for Answer Set Programming

Recent progress in logic programming (e.g., the development of the Answer Set Programming paradigm) has made it possible to teach it to general undergraduate and even high school students. Given the limited exposure of these students to computer science, the complexity of downloading, installing and using tools for writing logic programs could be a major barrier for logic programming to reach a much wider audience. We developed an online answer set programming environment with a self contained file system and a simple interface, allowing users to write logic programs and perform several tasks over the programs.

cs.OH↗

arXiv2016

Vicious Circle Principle and Formation of Sets in ASP Based Languages

The paper continues the investigation of Poincare and Russel's Vicious Circle Principle (VCP) in the context of the design of logic programming languages with sets. We expand previously introduced language Alog with aggregates by allowing infinite sets and several additional set related constructs useful for knowledge representation and teaching. In addition, we propose an alternative formalization of the original VCP and incorporate it into the semantics of new language, Slog+, which allows more liberal construction of sets and their use in programming rules. We show that, for programs without disjunction and infinite sets, the formal semantics of aggregates in Slog+ coincides with that of several other known languages. Their intuitive and formal semantics, however, are based on quite different ideas and seem to be more involved than that of Slog+.

cs.AI↗

arXiv2014

Vicious Circle Principle and Logic Programs with Aggregates

cs.AI↗

arXiv2013

SPARC - Sorted ASP with Consistency Restoring Rules

This is a preliminary report on the work aimed at making CR-Prolog -- a version of ASP with consistency restoring rules -- more suitable for use in teaching and large applications. First we describe a sorted version of CR-Prolog called SPARC. Second, we translate a basic version of the CR-Prolog into the language of DLV and compare the performance with the state of the art CR-Prolog solver. The results form the foundation for future more efficient and user friendly implementation of SPARC and shed some light on the relationship between two useful knowledge representation constructs: consistency restoring rules and weak constraints of DLV.

cs.PL↗

arXiv2010

Solving Functional Constraints by Variable Substitution

Functional constraints and bi-functional constraints are an important constraint class in Constraint Programming (CP) systems, in particular for Constraint Logic Programming (CLP) systems. CP systems with finite domain constraints usually employ CSP-based solvers which use local consistency, for example, arc consistency. We introduce a new approach which is based instead on variable substitution. We obtain efficient algorithms for reducing systems involving functional and bi-functional constraints together with other non-functional constraints. It also solves globally any CSP where there exists a variable such that any other variable is reachable from it through a sequence of functional constraints. Our experiments on random problems show that variable elimination can significantly improve the efficiency of solving problems with functional constraints.

cs.AI↗

arXiv2009

A Survey of Tree Convex Sets Test

Tree convex sets refer to a collection of sets such that each set in the collection is a subtree of a tree whose nodes are the elements of these sets. They extend the concept of row convex sets each of which is an interval over a total ordering of the elements of those sets. They have been applied to identify tractable Constraint Satisfaction Problems and Combinatorial Auction Problems. Recently, polynomial algorithms have been proposed to recognize tree convex sets. In this paper, we review the materials that are the key to a linear recognition algorithm.

cs.DS↗