arXiv subjects

Lei Sun

Publications and source records attributed to Lei Sun.

At least 109 records · Page 6Linked to original sources

arXiv2025

Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model

The rapid expansion of mobile internet has resulted in a substantial increase in user-generated content (UGC) images, thereby making the thorough assessment of UGC images both urgent and essential. Recently, multimodal large language models (MLLMs) have shown great potential in image quality assessment (IQA) and image aesthetic assessment (IAA). Despite this progress, effectively scoring the quality and aesthetics of UGC images still faces two main challenges: 1) A single score is inadequate to capture the hierarchical human perception. 2) How to use MLLMs to output numerical scores, such as mean opinion scores (MOS), remains an open question. To address these challenges, we introduce a novel dataset, named Realistic image Quality and Aesthetic (RealQA), including 14,715 UGC images, each of which is annoted with 10 fine-grained attributes. These attributes span three levels: low level (e.g., image clarity), middle level (e.g., subject integrity) and high level (e.g., composition). Besides, we conduct a series of in-depth and comprehensive investigations into how to effectively predict numerical scores using MLLMs. Surprisingly, by predicting just two extra significant digits, the next token paradigm can achieve SOTA performance. Furthermore, with the help of chain of thought (CoT) combined with the learnt fine-grained attributes, the proposed method can outperform SOTA methods on five public datasets for IQA and IAA with superior interpretability and show strong zero-shot generalization for video quality assessment (VQA). The code and dataset will be released.

cs.CV↗

arXiv2025

Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems

Recently, joint design approaches that simultaneously optimize optical systems and downstream algorithms through data-driven learning have demonstrated superior performance over traditional separate design approaches. However, current joint design approaches heavily rely on the manual identification of initial lenses, posing challenges and limitations, particularly for compound lens systems with multiple potential starting points. In this work, we present Quasi-Global Search Optics (QGSO) to automatically design compound lens based computational imaging systems through two parts: (i) Fused Optimization Method for Automatic Optical Design (OptiFusion), which searches for diverse initial optical systems under certain design specifications; and (ii) Efficient Physic-aware Joint Optimization (EPJO), which conducts parallel joint optimization of initial optical systems and image reconstruction networks with the consideration of physical constraints, culminating in the selection of the optimal solution in all search results. Extensive experimental results illustrate that QGSO serves as a transformative end-to-end lens design paradigm for superior global search ability, which automatically provides compound lens based computational imaging systems with higher imaging quality compared to existing paradigms. The source code will be made publicly available at https://github.com/LiGpy/QGSO.

eess.IV↗

arXiv2025

Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions

Controllable Depth-of-Field (DoF) imaging commonly produces amazing visual effects based on heavy and expensive high-end lenses. However, confronted with the increasing demand for mobile scenarios, it is desirable to achieve a lightweight solution with Minimalist Optical Systems (MOS). This work centers around two major limitations of MOS, i.e., the severe optical aberrations and uncontrollable DoF, for achieving single-lens controllable DoF imaging via computational methods. A Depth-aware Controllable DoF Imaging (DCDI) framework is proposed equipped with All-in-Focus (AiF) aberration correction and monocular depth estimation, where the recovered image and corresponding depth map are utilized to produce imaging results under diverse DoFs of any high-end lens via patch-wise convolution. To address the depth-varying optical degradation, we introduce a Depth-aware Degradation-adaptive Training (DA2T) scheme. At the dataset level, a Depth-aware Aberration MOS (DAMOS) dataset is established based on the simulation of Point Spread Functions (PSFs) under different object distances. Additionally, we design two plug-and-play depth-aware mechanisms to embed depth information into the aberration image recovery for better tackling depth-aware degradation. Furthermore, we propose a storage-efficient Omni-Lens-Field model to represent the 4D PSF library of various lenses. With the predicted depth map, recovered image, and depth-aware PSF map inferred by Omni-Lens-Field, single-lens controllable DoF imaging is achieved. Comprehensive experimental results demonstrate that the proposed framework enhances the recovery performance, and attains impressive single-lens controllable DoF imaging results, providing a seminal baseline for this field. The source code and the established dataset will be publicly available at https://github.com/XiaolongQian/DCDI.

cs.CV↗

arXiv2025

An Atomic Skill Library Construction Method for Data-Efficient Embodied Manipulation

Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks due to the complexity and diversity of real-world scenarios. The traditional end-to-end data collection and training manner leads to significant data demands. Decomposing end-to-end tasks into atomic skills helps reduce data requirements and improves the task success rate. However, existing methods are limited by predefined skill sets that cannot be dynamically updated. To address the issue, we introduce a three-wheeled data-driven method to build an atomic skill library. We divide tasks into subtasks using the Vision-Language-Planning (VLP). Then, atomic skill definitions are formed by abstracting the subtasks. Finally, an atomic skill library is constructed via data collection and Vision-Language-Action (VLA) fine-tuning. As the atomic skill library expands dynamically with the three-wheel update strategy, the range of tasks it can cover grows naturally. In this way, our method shifts focus from end-to-end tasks to atomic skills, significantly reducing data costs while maintaining high performance and enabling efficient adaptation to new tasks. Extensive experiments in real-world settings demonstrate the effectiveness and efficiency of our approach.

cs.RO↗

arXiv2025

Evolution of X-ray Gas in SN 1987A from 2007 to 2021: Ring Fading and Ejecta Brightening Unveiled through Differential Emission Measure Analysis

As the nearest supernova (SN) observed since Kepler's SN of 1604, SN 1987A provides an unprecedented opportunity to study in detail the early evolution of supernova remnants (SNRs). Despite extensive studies through both observations and simulations, there is still an urgent need for a more effective approach to integrate the results from two sides. In this study, we conducted a detailed differential emission measure (DEM) analysis on the XMM-Newton observations taken in 2007 to 2021 to characterize the continuous temperature structure of SN 1987A, which can be better compared with simulations. The X-ray plasma exhibit a temperature distribution with a major peak at $\sim0.5$-$1$ keV and a high-temperature tail extending to $\gtrsim5$ keV. The emission measure (EM) of the major peak started to decline around 2014, while the EM of the tail continued increasing and appears to have formed a secondary peak at $\sim3$-$5$ keV in recent years. Our DEM results consistent well with simulations, which help to further identify the major peak as originating from the equatorial ring and the secondary peak as arising from the newly shocked ejecta. Together with the simulations, our DEM analysis reveals recent fading of the ring and brightening of the ejecta in X-rays from SN 1987A. Additionally, we observed a recent decrease in the centroid energy of Fe K line, providing further evidence of newly shocked ejecta.

astro-ph.HE↗

arXiv2024

Block Coordinate Descent Methods for Structured Nonconvex Optimization with Nonseparable Constraints: Optimality Conditions and Global Convergence

Coordinate descent algorithms are widely used in machine learning and large-scale data analysis due to their strong optimality guarantees and impressive empirical performance in solving non-convex problems. In this work, we introduce Block Coordinate Descent (BCD) method for structured nonconvex optimization with nonseparable constraints. Unlike traditional large-scale Coordinate Descent (CD) approaches, we do not assume the constraints are separable. Instead, we account for the possibility of nonlinear coupling among them. By leveraging the inherent problem structure, we propose new CD methods to tackle this specific challenge. Under the relatively mild condition of locally bounded non-convexity, we demonstrate that achieving coordinate-wise stationary points offer a stronger optimality criterion compared to standard critical points. Furthermore, under the Luo-Tseng error bound conditions, our BCD methods exhibit Q-linear convergence to coordinate-wise stationary points or critical points. To demonstrate the practical utility of our methods, we apply them to various machine learning and signal processing models. We also provide the geometry analysis for the models. Experiments on real-world data consistently demonstrate the superior objective values of our approaches compared to existing methods.

math.OC↗

arXiv2024

Temporal-Mapping Photography for Event Cameras

Event cameras, or Dynamic Vision Sensors (DVS) are novel neuromorphic sensors that capture brightness changes as a continuous stream of "events" rather than traditional intensity frames. Converting sparse events to dense intensity frames faithfully has long been an ill-posed problem. Previous methods have primarily focused on converting events to video in dynamic scenes or with a moving camera. In this paper, for the first time, we realize events to dense intensity image conversion using a stationary event camera in static scenes with a transmittance adjustment device for brightness modulation. Different from traditional methods that mainly rely on event integration, the proposed Event-Based Temporal Mapping Photography (EvTemMap) measures the time of event emitting for each pixel. Then, the resulting Temporal Matrix is converted to an intensity frame with a temporal mapping neural network. At the hardware level, the proposed EvTemMap is implemented by combining a transmittance adjustment device with a DVS, named Adjustable Transmittance Dynamic Vision Sensor (AT-DVS). Additionally, we collected TemMat dataset under various conditions including low-light and high dynamic range scenes. The experimental results showcase the high dynamic range, fine-grained details, and high-grayscale resolution of the proposed EvTemMap. The code and dataset are available in https://github.com/YuHanBaozju/EvTemMap

cs.CV↗

arXiv2024

Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization

Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications. In this paper, in contrast to improving the simulation pipeline, we deliver a novel insight into real-world CAC from the perspective of Unsupervised Domain Adaptation (UDA). By incorporating readily accessible unpaired real-world data into training, we formalize the Domain Adaptive CAC (DACAC) task, and then introduce a comprehensive Real-world aberrated images (Realab) dataset to benchmark it. The setup task presents a formidable challenge due to the intricacy of understanding the target optical degradation domain. To this intent, we propose a novel Quantized Domain-Mixing Representation (QDMR) framework as a potent solution to the issue. Centering around representing and quantizing the optical degradation which is consistent across different images, QDMR adapts the CAC model to the target domain from three key aspects: (1) reconstructing aberrated images of both domains by a VQGAN to learn a Domain-Mixing Codebook (DMC) characterizing the optical degradation; (2) modulating the deep features in CAC model with DMC to transfer the target domain knowledge; and (3) leveraging the trained VQGAN to generate pseudo target aberrated images from the source ones for convincing target domain supervision. Extensive experiments on both synthetic and real-world benchmarks reveal that the models with QDMR consistently surpass the competitive methods in mitigating the synthetic-to-real gap, which produces visually pleasant real-world CAC results with fewer artifacts. Codes and datasets are made publicly available at https://github.com/zju-jiangqi/QDMR.

cs.CV↗

arXiv2024

UVCANDELS: Catalogs of photometric redshifts and galaxy physical properties

The UltraViolet imaging of the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey Fields (UVCANDELS) program provides deep HST F275W and F435W imaging over four CANDELS fields (GOODS-N, GOODS-S, COSMOS, and EGS). We combine this newly acquired UV imaging with existing HST imaging from CANDELS as well as existing ancillary data to obtain robust photometric redshifts and reliable estimates for galaxy physical properties for over 150,000 galaxies in the $\sim$430 arcmin$^2$ UVCANDELS area. Here, we leverage the power of the new UV photometry to not only improve the photometric redshift measurements in these fields, but also constrain the full redshift probability distribution combining multiple redshift fitting tools. Furthermore, using the full UV-to-IR photometric dataset, we measure the galaxy physical properties by fitting templates from population synthesis models with two different parameterizations (flexible and fixed-form) of the star-formation histories (SFHs). Compared to the flexible SFH parametrization, we find that the fixed-form SFHs systematically underestimate the galaxy stellar masses, both at the low- ($\lesssim10^9 M_\odot$) and high- ($\gtrsim10^{10} M_\odot$) mass end, by as much as $\sim0.5$ dex. This underestimation is primarily due the limited ability of fixed-form SFH parameterization to simultaneously capture the chaotic nature of star-formation in these galaxies.

astro-ph.GA↗

arXiv2024

Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs

Large Language Models (LLMs) possess impressive reasoning abilities but are prone to generating incorrect information, often referred to as hallucinations. While incorporating external Knowledge Graphs (KGs) can partially mitigate this issue, existing methods primarily treat KGs as static knowledge repositories, overlooking the critical disparity between KG and LLM knowledge, and failing to fully exploit the reasoning capabilities inherent in KGs. To address these limitations, we propose Pyramid-Driven Alignment (PDA), a novel framework for seamlessly integrating LLMs with KGs. PDA utilizes Pyramid Principle analysis to construct a hierarchical pyramid structure. This structure is designed to reflect the input question and generate more validated deductive knowledge, thereby enhancing the alignment of LLMs and KGs and ensuring more cohesive integration. Furthermore, PDA employs a recursive mechanism to harness the underlying reasoning abilities of KGs, resulting in more accurate knowledge retrieval for question-answering tasks. Our experimental results reveal a substantial performance advantage of PDA over state-of-the-art baselines, with improvements reaching 26.70% and 26.78%.

cs.CL↗

arXiv2024

The Mitochondrial Genome of Cathaya argyrophylla Reaches 18.99 Mb: Analysis of Super-Large Mitochondrial Genomes in Pinaceae

Mitochondrial genomes in the Pinaceae family are notable for their large size and structural complexity. In this study, we sequenced and analyzed the mitochondrial genome of Cathaya argyrophylla, an endangered and endemic Pinaceae species, uncovering a genome size of 18.99 Mb, meaning the largest mitochondrial genome reported to date. To investigate the mechanisms behind this exceptional size, we conducted comparative analyses with other Pinaceae species possessing both large and small mitochondrial genomes, as well as with other gymnosperms. We focused on repeat sequences, transposable element activity, RNA editing events, chloroplast-derived sequence transfers (mtpts), and sequence homology with nuclear genomes. Our findings indicate that while Cathaya argyrophylla and other extremely large Pinaceae mitochondrial genomes contain substantial amounts of repeat sequences and show increased activity of LINEs and LTR retrotransposons, these factors alone do not fully account for the genome expansion. Notably, we observed a significant incorporation of chloroplast-derived sequences in Cathaya argyrophylla and other large mitochondrial genomes, suggesting that extensive plastid-to-mitochondrial DNA transfer may play a crucial role in genome enlargement. Additionally, large mitochondrial genomes exhibited distinct patterns of RNA editing and limited similarity with nuclear genomes compared to smaller genomes. These results suggest that the massive mitochondrial genomes in Pinaceae are likely the result of multiple contributing factors, including repeat sequences, transposon activity, and extensive plastid sequence incorporation. Our study enhances the understanding of mitochondrial genome evolution in plants and provides valuable genetic information for the conservation and study of Cathaya argyrophylla.

q-bio.GN↗

arXiv2024

Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues

Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. Current research predominantly treats personality recognition as a classification task, failing to reveal the supporting evidence for the recognized personality. In this paper, we propose a novel task named Explainable Personality Recognition, aiming to reveal the reasoning process as supporting evidence of the personality trait. Inspired by personality theories, personality traits are made up of stable patterns of personality state, where the states are short-term characteristic patterns of thoughts, feelings, and behaviors in a concrete situation at a specific moment in time. We propose an explainable personality recognition framework called Chain-of-Personality-Evidence (CoPE), which involves a reasoning process from specific contexts to short-term personality states to long-term personality traits. Furthermore, based on the CoPE framework, we construct an explainable personality recognition dataset from dialogues, PersonalityEvd. We introduce two explainable personality state recognition and explainable personality trait recognition tasks, which require models to recognize the personality state and trait labels and their corresponding support evidence. Our extensive experiments based on Large Language Models on the two tasks show that revealing personality traits is very challenging and we present some insights for future research. Our data and code are available at https://github.com/Lei-Sun-RUC/PersonalityEvd.

cs.CL↗

arXiv2024

On modeling NP-Complete problems as polynomial-sized linear programs: Escaping/Side-stepping the "barriers"

In view of the extended formulations (EFs) developments (e.g. "Fiorini, S., S. Massar, S. Pokutta, H.R. Tiwary, and R. de Wolf [2015]. Exponential Lower Bounds for Polytopes in Combinatorial Optimization. Journal of the ACM 62:2"), we focus in this paper on the question of whether it is possible to model an NP-Complete problem as a polynomial-sized linear program. For the sake of simplicity of exposition, the discussions are focused on the TSP. We show that a finding that there exists no polynomial-sized extended formulation of "the TSP polytope" does not (necessarily) imply that it is "impossible" for a polynomial-sized linear program to solve the TSP optimization problem. We show that under appropriate conditions the TSP optimization problem can be solved without recourse to the traditional city-to-city ("travel leg") variables, thereby side-stepping/"escaping from" "the TSP polytope" and hence, the barriers. Some illustrative examples are discussed.

cs.CC↗

arXiv2024

Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers

High-quality panoramic images with a Field of View (FoV) of 360° are essential for contemporary panoramic computer vision tasks. However, conventional imaging systems come with sophisticated lens designs and heavy optical components. This disqualifies their usage in many mobile and wearable applications where thin and portable, minimalist imaging systems are desired. In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging. With less than three spherical lenses, a Minimalist Panoramic Imaging Prototype (MPIP) is constructed based on the design of the Panoramic Annular Lens (PAL), but with low-quality imaging results due to aberrations and small image plane size. We propose two pipelines, i.e. Aberration Correction (AC) and Super-Resolution and Aberration Correction (SR&AC), to solve the image quality problems of MPIP, with imaging sensors of small and large pixel size, respectively. To leverage the prior information of the optical system, we propose a Point Spread Function (PSF) representation method to produce a PSF map as an additional modality. A PSF-aware Aberration-image Recovery Transformer (PART) is designed as a universal network for the two pipelines, in which the self-attention calculation and feature extraction are guided by the PSF map. We train PART on synthetic image pairs from simulation and put forward the PALHQ dataset to fill the gap of real-world high-quality PAL images for low-level vision. A comprehensive variety of experiments on synthetic and real-world benchmarks demonstrates the impressive imaging results of PCIE and the effectiveness of the PSF representation. We further deliver heuristic experimental findings for minimalist and high-quality panoramic imaging. Our dataset and code will be available at https://github.com/zju-jiangqi/PCIE-PART.

cs.CV↗

arXiv2024

Outlier-Robust Geometric Perception: A Novel Thresholding-Based Estimator with Intra-Class Variance Maximization

Geometric perception problems are fundamental tasks in robotics and computer vision. In real-world applications, they often encounter the inevitable issue of outliers, preventing traditional algorithms from making correct estimates. In this paper, we present a novel general-purpose robust estimator TIVM (Thresholding with Intra-class Variance Maximization) that can collaborate with standard non-minimal solvers to efficiently reject outliers for geometric perception problems. First, we introduce the technique of intra-class variance maximization to design a dynamic 2-group thresholding method on the measurement residuals, aiming to distinctively separate inliers from outliers. Then, we develop an iterative framework that robustly optimizes the model by approaching the pure-inlier group using a multi-layered dynamic thresholding strategy as subroutine, in which a self-adaptive mechanism for layer-number tuning is further employed to minimize the user-defined parameters. We validate the proposed estimator on 3 classic geometric perception problems: rotation averaging, point cloud registration and category-level perception, and experiments show that it is robust against 70--90\% of outliers and can converge typically in only 3--15 iterations, much faster than state-of-the-art robust solvers such as RANSAC, GNC and ADAPT. Furthermore, another highlight is that: our estimator can retain approximately the same level of robustness even when the inlier-noise statistics of the problem are fully unknown.

cs.CV↗

arXiv2024

Thermal X-ray Emission in the Western Half of the LMC Superbubble 30 Dor C

While 30 Dor C is a unique superbubble in the Large Magellanic Cloud for its luminous non-thermal X-ray emission, the thermal X-ray emission it emanates has not yet been thoroughly investigated and well constrained. Based on the separate ~1 Ms deep XMM-Newton and Chandra observations, we report the discovery of the thermally-emitting plasma in some portions of the western half of 30 Dor C. The thermal emission can be reproduced by a collisional-ionization-equilibrium plasma model with an average electron temperature of ~0.4 keV. We find a significant overabundance of the intermediate-mass elements such as O, Ne, Mg, and Si, which may be indicative of a recent supernova explosion in 30 Dor C. Dynamical properties in combination with the information of the OB association LH 90 suggest that the internal post-main-sequence stars dominate the power of the superbubble and blow it out in the past ~1 Myr.

astro-ph.HE↗

arXiv2024

Spin-lattice relaxation with non-linear couplings: Comparison between Fermi's golden rule and extended dissipaton equation of motion

Fermi's golden rule (FGR) offers an empirical framework for understanding the dynamics of spin-lattice relaxation in magnetic molecules, encompassing mechanisms like direct (one-phonon) and Raman (two-phonon) processes. These principles effectively model experimental longitudinal relaxation rates, denoted as $T_1^{-1}$. However, under scenarios of increased coupling strength and nonlinear spin-lattice interactions, FGR's applicability may diminish. This paper numerically evaluates the exact spin-lattice relaxation rate kernels, employing the extended dissipaton equation of motion (DEOM) formalism. Our calculations reveal that when quadratic spin-lattice coupling is considered, the rate kernels exhibit a free induction decay-like feature, and the damping rates depend on the interaction strength. We observe that the temperature dependence predicted by FGR significantly deviates from the exact results since FGR ignores the non-Markovian nature of spin-lattice relaxation. Our methods can be readily applied to other systems with nonlinear spin-lattice interactions and provide valuable insights into the temperature dependence of $T_1$ in molecular qubits.

physics.chem-ph↗

arXiv2024

Empowering Embodied Manipulation: A Bimanual-Mobile Robot Manipulation Dataset for Household Tasks

The advancements in embodied AI are increasingly enabling robots to tackle complex real-world tasks, such as household manipulation. However, the deployment of robots in these environments remains constrained by the lack of comprehensive bimanual-mobile robot manipulation data that can be learned. Existing datasets predominantly focus on single-arm manipulation tasks, while the few dual-arm datasets available often lack mobility features, task diversity, comprehensive sensor data, and robust evaluation metrics; they fail to capture the intricate and dynamic nature of household manipulation tasks that bimanual-mobile robots are expected to perform. To overcome these limitations, we propose BRMData, a Bimanual-mobile Robot Manipulation Dataset specifically designed for household applications. BRMData encompasses 10 diverse household tasks, including single-arm and dual-arm tasks, as well as both tabletop and mobile manipulations, utilizing multi-view and depth-sensing data information. Moreover, BRMData features tasks of increasing difficulty, ranging from single-object to multi-object grasping, non-interactive to human-robot interactive scenarios, and rigid-object to flexible-object manipulation, closely simulating real-world household applications. Additionally, we introduce a novel Manipulation Efficiency Score (MES) metric to evaluate both the precision and efficiency of robot manipulation methods in household tasks. We thoroughly evaluate and analyze the performance of advanced robot manipulation learning methods using our BRMData, aiming to drive the development of bimanual-mobile robot manipulation technologies. The dataset is now open-sourced and available at https://embodiedrobot.github.io/.

cs.RO↗