arXiv subjects

Lei Sun

Publications and source records attributed to Lei Sun.

At least 91 records · Page 5Linked to original sources

arXiv2025

RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space

Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordinate system and perform motion editing directly in the 3D space. Trajectory control is implemented by unprojecting edited 2D trajectories into 3D with focal-length calibration and coordinate transformation, followed by speed alignment and orientation adjustment; actions are supplied by a motion bank or generated via text-to-motion methods. Then, based on modern text-to-video diffusion transformer models, we inject the subject as tokens for full attention, concatenate the background along the channel dimension, and add motion (trajectory and action) control signals by addition. Such a design opens up the possibility for us to generate realistic videos of anyone doing anything anywhere. Extensive experiments on benchmark datasets and real-world cases demonstrate that our method achieves state-of-the-art performance on both element-wise controllability and overall video quality.

cs.CV↗

arXiv2025

Latent Swap Joint Diffusion for 2D Long-Form Latent Generation

This paper introduces Swap Forward (SaFa), a modality-agnostic and efficient method to generate seamless and coherence long spectrum and panorama through latent swap joint diffusion across multi-views. We first investigate the spectrum aliasing problem in spectrum-based audio generation caused by existing joint diffusion methods. Through a comparative analysis of the VAE latent representation of Mel-spectra and RGB images, we identify that the failure arises from excessive suppression of high-frequency components during the spectrum denoising process due to the averaging operator. To address this issue, we propose Self-Loop Latent Swap, a frame-level bidirectional swap applied to the overlapping region of adjacent views. Leveraging stepwise differentiated trajectories of adjacent subviews, this swap operator adaptively enhances high-frequency components and avoid spectrum distortion. Furthermore, to improve global cross-view consistency in non-overlapping regions, we introduce Reference-Guided Latent Swap, a unidirectional latent swap operator that provides a centralized reference trajectory to synchronize subview diffusions. By refining swap timing and intervals, we can achieve a cross-view similarity-diversity balance in a forward-only manner. Quantitative and qualitative experiments demonstrate that SaFa significantly outperforms existing joint diffusion methods and even training-based methods in audio generation using both U-Net and DiT models, along with effective longer length adaptation. It also adapts well to panorama generation, achieving comparable performance with 2 $\sim$ 20 $\times$ faster speed and greater model generalizability. More generation demos are available at https://swapforward.github.io/

cs.SD↗

arXiv2025

Accuracy and Security-Guaranteed Participant Selection and Beamforming Design for RIS-Assisted Federated Learning

Federated learning (FL) has emerged as an effective approach for training neural network models without requiring the sharing of participants' raw data, thereby addressing data privacy concerns. In this paper, we propose a reconfigurable intelligent surface (RIS)-assisted FL framework in the presence of eavesdropping, where partial edge devices are selected to participate in the FL training process. In contrast, the remaining devices serve as cooperative jammers by transmitting jamming signals to disrupt eavesdropping. We aim to minimize the training latency in each FL round by jointly optimizing participant selection, bandwidth allocation, and RIS beamforming design, subject to the convergence accuracy of FL and the secure uploading requirements. To solve the resulting mixed-integer nonlinear programming problem, we propose a twin delayed deep deterministic policy gradient (TD3) algorithm. Simulation results demonstrate that the proposed scheme reduces the FL training latency by approximately 27$\%$ compared to baselines.

cs.IT↗

arXiv2025

The physical origin of positive metallicity radial gradients in high-redshift galaxies: insights from the FIRE-2 cosmological hydrodynamic simulations

Using the FIRE-2 cosmological zoom-in simulations, we investigate the temporal evolution of gas-phase metallicity radial gradients of Milky Way-mass progenitors in the redshift range of $0.4<z<3$. We pay special attention to the occurrence of positive (i.e. inverted) metallicity gradients -- where metallicity increases with galactocentric radius. This trend, contrary to the more commonly observed negative radial gradients, has been frequently seen in recent spatially resolved grism observations. The rate of occurrence of positive gradients in FIRE-2 is about $\sim7\%$ for $0.4<z<3$ and $\sim13\%$ at higher redshifts ($1.5<z<3$), broadly consistent with observations. Moreover, we investigate the correlations among galaxy metallicity gradient, stellar mass, star formation rate (SFR), and degree of rotational support. Metallicity gradients show a strong correlation with both sSFR and the rotational-to-dispersion velocity ratio ($v_c/σ$), implying that starbursts and kinematic morphology of galaxies play significant roles in shaping these gradients. The FIRE-2 simulations indicate that galaxies with high sSFR (${\rm log(sSFR~[yr^{-1}])}\gtrsim-9.2$) and weak rotational support ($v_c/σ\lesssim 1$) are more likely -- by $\sim$15\% -- to develop positive metallicity gradients. This trend is attributed to galaxy-scale gas flows driven by stellar feedback, which effectively redistribute metals within the interstellar medium. Our results support the important role of stellar feedback in governing the chemo-structural evolution and disk formation of Milky Way-mass galaxies at the cosmic noon epoch.

astro-ph.GA↗

arXiv2025

Ultralong Room-Temperature Qubit Lifetimes of Covalent Organic Frameworks

Molecular electron spin qubits offer atomic-level tunability and room-temperature quantum coherence. Their integration into engineered solid-state matrices can enhance performance towards ambient quantum information technologies. Herein, we demonstrate covalent organic frameworks (COFs) as programmable matrices of stable organic radical qubits allowing strategic optimization of spin-phonon and spin-spin interactions. Using two classic boronate-ester frameworks, COF-5 and COF-108, to host semiquinone-like radical qubits, we achieve ultralong spin relaxation time (T1 > 300 μs) at 298 K, which outperforms most molecular qubits and rivals inorganic spin defects. The suppression of spin relaxation is attributed to rigid and neutral structures as well as carbon-centered spin distributions that effectively weaken spin-phonon coupling. Employing dynamical decoupling methods to both COFs improves their quantum coherence and enables room-temperature detection of nuclear spins including 1H, 11B, and 13C. Our work establishes COFs as designer quantum materials, opening new avenues for quantum sensing of nuclear spins at room temperature.

quant-ph↗

arXiv2025

A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild

Effective video frame interpolation hinges on the adept handling of motion in the input scene. Prior work acknowledges asynchronous event information for this, but often overlooks whether motion induces blur in the video, limiting its scope to sharp frame interpolation. We instead propose a unified framework for event-based frame interpolation that performs deblurring ad-hoc and thus works both on sharp and blurry input videos. Our model consists in a bidirectional recurrent network that incorporates the temporal dimension of interpolation and fuses information from the input frames and the events adaptively based on their temporal proximity. To enhance the generalization from synthetic data to real event cameras, we integrate self-supervised framework with the proposed model to enhance the generalization on real-world datasets in the wild. At the dataset level, we introduce a novel real-world high-resolution dataset with events and color videos named HighREV, which provides a challenging evaluation setting for the examined task. Extensive experiments show that our network consistently outperforms previous state-of-the-art methods on frame interpolation, single image deblurring, and the joint task of both. Experiments on domain transfer reveal that self-supervised training effectively mitigates the performance degradation observed when transitioning from synthetic data to real-world data. Code and datasets are available at https://github.com/AHupuJR/REFID.

cs.CV↗

arXiv2025

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in conjunction with multiple images, poses significant challenges, which is mainly due to the lack of advanced reasoning ability across diverse multi-modal contexts. In this work, we aim to address the more practical universal grounding task, and propose UniVG-R1, a reasoning guided multimodal large language model (MLLM) for universal visual grounding, which enhances reasoning capabilities through reinforcement learning (RL) combined with cold-start data. Specifically, we first construct a high-quality Chain-of-Thought (CoT) grounding dataset, annotated with detailed reasoning chains, to guide the model towards correct reasoning paths via supervised fine-tuning. Subsequently, we perform rule-based reinforcement learning to encourage the model to identify correct reasoning chains, thereby incentivizing its reasoning capabilities. In addition, we identify a difficulty bias arising from the prevalence of easy samples as RL training progresses, and we propose a difficulty-aware weight adjustment strategy to further strengthen the performance. Experimental results demonstrate the effectiveness of UniVG-R1, which achieves state-of-the-art performance on MIG-Bench with a 9.1% improvement over the previous method. Furthermore, our model exhibits strong generalizability, achieving an average improvement of 23.4% in zero-shot performance across four image and video reasoning grounding benchmarks. The project page can be accessed at https://amap-ml.github.io/UniVG-R1-page/.

cs.CV↗

arXiv2025

MAGI-1: Autoregressive Video Generation at Scale

We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai.

cs.CV↗

arXiv2025

Towards Anytime Optical Flow Estimation with Event Cameras

Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting the research potential of event-driven optical flow. To address this challenge, we introduce a low-latency event representation, Unified Voxel Grid, and propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. Furthermore, we propose the Rectified Flow Warp Loss (RFWL) for the unsupervised assessment of intermediate optical flow. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.

cs.CV↗

arXiv2025

NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap

SLAM systems based on Gaussian Splatting have garnered attention due to their capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatting SLAM systems usually struggle with large scene representation and lack effective loop closure detection. To address these issues, we introduce NGM-SLAM, the first 3DGS based SLAM system that utilizes neural radiance field submaps for progressive scene expression, effectively integrating the strengths of neural radiance fields and 3D Gaussian Splatting. We utilize neural radiance field submaps as supervision and achieve high-quality scene expression and online loop closure adjustments through Gaussian rendering of fused submaps. Our results on multiple real-world scenes and large-scale scene datasets demonstrate that our method can achieve accurate hole filling and high-quality scene expression, supporting monocular, stereo, and RGB-D inputs, and achieving state-of-the-art scene reconstruction and tracking performance.

cs.RO↗

arXiv2025

NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

cs.CV↗

arXiv2025

The Tenth NTIRE 2025 Image Denoising Challenge Report

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on computational complexity or model size. The task assumes independent additive white Gaussian noise (AWGN) with a fixed noise level of 50. A total of 290 participants registered for the challenge, with 20 teams successfully submitting valid results, providing insights into the current state-of-the-art in image denoising.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results

This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal of the challenge is to design an event-based method that achieves high-quality image deblurring, with performance quantitatively assessed using Peak Signal-to-Noise Ratio (PSNR). Notably, there are no restrictions on computational complexity or model size. The task focuses on leveraging both events and images as inputs for single-image deblurring. A total of 199 participants registered, among whom 15 teams successfully submitted valid results, offering valuable insights into the current state of event-based image deblurring. We anticipate that this challenge will drive further advancements in event-based vision research.

cs.CV↗

arXiv2025

FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos

Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos are inherently complex, making overall scoring notoriously difficult. In this paper, we emphasize the critical importance of integrating fine-grained reasoning into video evaluation, and we propose $\textbf{F}$ing$\textbf{ER}$, a novel entity-level reasoning evaluation framework that first automatically generates $\textbf{F}$ine-grained $\textbf{E}$ntity-level questions, and then answers those questions by a $\textbf{R}$easoning model with scores, which can be subsequently weighted summed to an overall score for different applications. Specifically, we leverage LLMs to derive entity-level questions across five distinct perspectives, which (i) often focus on some specific entities of the content, thereby making answering or scoring much easier by MLLMs, and (ii) are more interpretable. Then we construct a FingER dataset, consisting of approximately 3.3k videos and corresponding 60k fine-grained QA annotations, each with detailed reasons. Based on that, we further investigate various training protocols to best incentivize the reasoning capability of MLLMs for correct answer prediction. Extensive experiments demonstrate that a reasoning model trained using Group Relative Policy Optimization (GRPO) with a cold-start strategy achieves the best performance. Notably, our model surpasses existing methods by a relative margin of $11.8\%$ on GenAI-Bench and $5.5\%$ on MonetBench with only 3.3k training videos, which is at most one-tenth of the training samples utilized by other methods. Our code and dataset will be released soon.

cs.CV↗

arXiv2025

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep models that optimize key computational metrics, i.e., runtime, parameters, and FLOPs, while achieving a PSNR of at least 26.90 dB on the $\operatorname{DIV2K\_LSDIR\_valid}$ dataset and 26.99 dB on the $\operatorname{DIV2K\_LSDIR\_test}$ dataset. A robust participation saw \textbf{244} registered entrants, with \textbf{43} teams submitting valid entries. This report meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques. The analysis highlights innovative approaches and establishes benchmarks for future research in the field.

cs.CV↗

arXiv2025

Low-Light Image Enhancement using Event-Based Illumination Estimation

Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. Prevalent event-based solutions primarily utilize events triggered by motion, i.e., ''motion events'' to strengthen only the edge texture, while leaving the high dynamic range and excellent low-light responsiveness of event cameras largely unexplored. This paper instead opens a new avenue from the perspective of estimating the illumination using ''temporal-mapping'' events, i.e., by converting the timestamps of events triggered by a transmittance modulation into brightness values. The resulting fine-grained illumination cues facilitate a more effective decomposition and enhancement of the reflectance component in low-light images through the proposed Illumination-aided Reflectance Enhancement module. Furthermore, the degradation model of temporal-mapping events under low-light condition is investigated for realistic training data synthesizing. To address the lack of datasets under this regime, we construct a beam-splitter setup and collect EvLowLight dataset that includes images, temporal-mapping events, and motion events. Extensive experiments across 5 synthetic datasets and our real-world EvLowLight dataset substantiate that the devised pipeline, dubbed RetinEV, excels in producing well-illuminated, high dynamic range images, outperforming previous state-of-the-art event-based methods by up to 6.62 dB, while maintaining an efficient inference speed of 35.6 frame-per-second on a 640X480 image.

cs.CV↗

arXiv2025

SGE: Structured Light System Based on Gray Code with an Event Camera

Fast and accurate depth sensing has long been a significant research challenge. Event camera, as a device that quickly responds to intensity changes, provides a new solution for structured light (SL) systems. In this paper, we introduce Gray code into event-based SL systems for the first time. Our setup includes an event camera and a Digital Light Processing (DLP) projector, enabling depth estimation through high-speed projection and decoding of Gray code patterns. By employing Gray code for point matching in event-based SL system, our method is immune to timestamp noise, realizing high-speed depth estimation without loss of accuracy and spatial resolution. The binary nature of events and Gray code minimizes data redundancy, enabling us to fully utilize sensor bandwidth at 100%. Experimental results show that our approach achieves accuracy comparable to state-of-the-art scanning methods while surpassing them in data acquisition speed (up to 41 times improvement) without sacrificing accuracy and spatial resolution. Our proposed approach offers a highly promising solution for ultra-fast, real-time, and high-precision dense depth estimation.

cs.CV↗

arXiv2025

Unusual X-ray Oxygen Line Ratios of SN 1987A Arising From the Absorption of Galactic Hot Interstellar Medium

Recent high-resolution X-ray spectroscopic studies have revealed unusual oxygen line ratios, such as the high O VII forbidden-to-resonance ratio, in several supernova remnants. While the physical origin is still under debate, for most of them, it has been suggested that this phenomenon arises from either charge exchange (CX) or resonant scattering (RS). In this work, we report the high O VII G-ratio ($\gtrsim1$) and high O VIII Ly$β$/Ly$α$ ratio ($\gtrsim0.2$) found in multiepoch XMM-Newton RGS observations of SN 1987A. The line ratios cannot be fully explained by non-equilibrium ionization effects, CX, or RS. We suggest the absorption of foreground hot gas as the most likely origin, which plays the major role in modifying line fluxes and line ratios. Based on this scenario, we introduced two Gaussian absorption components at the O VII resonance line and the O VIII Ly$α$ line and constrained the optical depth of the two lines as $τ_{\rm OVII}\sim0.6$ and $τ_{\rm OVIII}\sim0.2$. We estimated the temperature as $kT_{\rm e}\sim0.15$ keV and the oxygen column density as $N_{\rm O}\sim0.5\times10^{16}$ cm$^{-2}$ for the absorbing gas, which is consistent with the hot interstellar medium in the Galactic halo. Neglecting this absorption component may lead to an underestimation of the O abundance. We revised the O abundance of SN 1987A, which is increased by $\sim20\%$ compared with previous results. The N/O ratio by number of atoms is revised to be $\sim1.2$.

astro-ph.HE↗