arXiv subjects

Jun Chen

Publications and source records attributed to Jun Chen.

At least 163 records · Page 9Linked to original sources

arXiv2025

Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure

This paper studies the rate-distortion-perception (RDP) tradeoff for a memoryless source model in the asymptotic limit of large block-lengths. The perception measure is based on a divergence between the distributions of the source and reconstruction sequences \emph{conditioned} on the encoder output, first proposed by Mentzer et al. We consider the case when there is no shared randomness between the encoder and the decoder and derive a single-letter characterization of the RDP function for the case of discrete memoryless sources. This is in contrast to the marginal-distribution metric case (introduced by Blau and Michaeli), whose RDP characterization remains open when there is no shared randomness. The achievability scheme is based on lossy source coding with a posterior reference map. For the case of continuous valued sources under the squared error distortion measure and the squared quadratic Wasserstein perception measure, we also derive a single-letter characterization and show that the decoder can be restricted to a noise-adding mechanism. Interestingly, the RDP function characterized for the case of zero perception loss coincides with that of the marginal metric, and further zero perception loss can be achieved with a 3-dB penalty in minimum distortion. Finally we specialize to the case of Gaussian sources, and derive the RDP function for Gaussian vector case and propose a reverse water-filling type solution. We also partially characterize the RDP function for a mixture of Gaussian vector sources.

cs.IT↗

arXiv2025

Kimi-Audio Technical Report

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

eess.AS↗

arXiv2025

Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space

We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure. Moreover, it is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source. Various notions of universal representation are also clarified.

cs.IT↗

arXiv2025

Designing Optimal Distorted-Octahedra Superlattices for Strong Topological Hall Effect

Topologically protected spin states hold great promise for applications in next generation of memory circuits and spintronic devices. These intriguing textures typically emerge in bulk materials or heterostructures with broken inversion symmetry, accompanied by an enhanced Dzyaloshinskii-Moriya interaction (DMI). In this study, we successfully induced the topological Hall effect (THE) in atomically designed (DyScO3)n/(SrRuO3)n (DnSn) superlattices over a significant range of temperatures (10~120K) and thicknesses (16~40nm). Using magnetic force microscopy (MFM), we observed the formation and stability of magnetic domains, such as topological skyrmions. By precisely controlling the interlayer thickness (n) and biaxial strain, we elucidated the mechanisms underlying the modulation and induction of magnetic topological states. Supporting evidence was provided by scanning transmission electron microscopy (STEM) and X-ray absorption spectroscopy (XAS), thereby lending further credence to our conclusions. These heterostructures offer a universal method for exploring topological phenomena driven by distorted octahedra, while enhancing the integrability and addressability of topologically protected functional devices.

cond-mat.mtrl-sci↗

arXiv2025

NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are developed and evaluated using our collected real-world Raindrop Clarity dataset. Unlike existing deraining datasets, our Raindrop Clarity dataset is more diverse and challenging in degradation types and contents, which includes day raindrop-focused, day background-focused, night raindrop-focused, and night background-focused degradations. This dataset is divided into three subsets for competition: 14,139 images for training, 240 images for validation, and 731 images for testing. The primary objective of this challenge is to establish a new and powerful benchmark for the task of removing raindrops under varying lighting and focus conditions. There are a total of 361 participants in the competition, and 32 teams submitting valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the Raindrop Clarity dataset. The project can be found at https://lixinustc.github.io/CVPR-NTIRE2025-RainDrop-Competition.github.io/.

cs.CV↗

arXiv2025

Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design

Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors. Moreover, we develop a CNN-Transformer Hybrid Structure-Guided Feature Extractor (HSGFE) module at each scale with in the UNet encoder-decoder architecture. Besides the CNN blocks which excels in multi-scale feature extraction and fusion, we introduce a Structure-Guided Transformer Block (SGTB) in each HSGFE that incorporates structural priors to modulate the enhancement process. Extensive experiments show that our method achieves state-of-the-art performance on several LLIE benchmarks in both quantitative metrics and visual quality. Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge. Code is released at https://github.com/minyan8/imagine.

cs.CV↗

arXiv2025

Retinex-guided Histogram Transformer for Mask-free Shadow Removal

While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes. In this work, we propose ReHiT, an efficient mask-free shadow removal framework based on a hybrid CNN-Transformer architecture guided by Retinex theory. We first introduce a dual-branch pipeline to separately model reflectance and illumination components, and each is restored by our developed Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Second, besides the CNN-based blocks that are capable of learning residual dense features and performing multi-scale semantic fusion, multi-scale semantic fusion, we develop the Illumination-Guided Histogram Transformer Block (IGHB) to effectively handle non-uniform illumination and spatially complex shadows. Extensive experiments on several benchmark datasets validate the effectiveness of our approach over existing mask-free methods. Trained solely on the NTIRE 2025 Shadow Removal Challenge dataset, our solution delivers competitive results with one of the smallest parameter sizes and fastest inference speeds among top-ranked entries, highlighting its applicability for real-world applications with limited computational resources. The code is available at https://github.com/dongw22/oath.

cs.CV↗

arXiv2025

Low-Complexity AoI-Optimal Status Update Control with Partial Battery State Information in Energy Harvesting IoT Networks

For a two-hop IoT system consisting of multiple energy harvesting sensors, a cache-enabled edge node, and multiple monitors, the status update control at the edge node, which has partial battery state information (pBSI) of the sensors, is formulated as a pBSI problem. The concept of inferred pBSI is introduced to reduce the noiseless single-sensor pBSI problem to a Markov decision process with a moderate state-space size, enabling the optimal policy to be obtained through a value iteration algorithm. A lower bound on the expected time-average on-demand age of information performance is established for the general single-sensor status update problem. For the single-sensor pBSI problem, a semi-closed-form policy called the current-next (CN) policy is proposed, along with an efficient post-update value iteration algorithm with a per-iteration time complexity proportional to the square of the battery capacity. A weighted-update-gain-competition (WUGC) approach is further leveraged to extend the CN policy to the multi-sensor case. Numerical results in the single-sensor case demonstrate the near-optimal performance of the CN policy across various energy arrival processes. Simulations for an IoT system with $100$ sensors reveal that the WUGC-CN policy outperforms the maximum-age-first policy and the random-scheduling-based CN policy under Bernoulli energy arrival processes.

cs.IT↗

arXiv2025

LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors

Directly employing 3D Gaussian Splatting (3DGS) on images with adverse illumination conditions exhibits considerable difficulty in achieving high-quality, normally-exposed representations due to: (1) The limited Structure from Motion (SfM) points estimated in adverse illumination scenarios fail to capture sufficient scene details; (2) Without ground-truth references, the intensive information loss, significant noise, and color distortion pose substantial challenges for 3DGS to produce high-quality results; (3) Combining existing exposure correction methods with 3DGS does not achieve satisfactory performance due to their individual enhancement processes, which lead to the illumination inconsistency between enhanced images from different viewpoints. To address these issues, we propose LITA-GS, a novel illumination-agnostic novel view synthesis method via reference-free 3DGS and physical priors. Firstly, we introduce an illumination-invariant physical prior extraction pipeline. Secondly, based on the extracted robust spatial structure prior, we develop the lighting-agnostic structure rendering strategy, which facilitates the optimization of the scene structure and object appearance. Moreover, a progressive denoising module is introduced to effectively mitigate the noise within the light-invariant representation. We adopt the unsupervised strategy for the training of LITA-GS and extensive experiments demonstrate that LITA-GS surpasses the state-of-the-art (SOTA) NeRF-based method while enjoying faster inference speed and costing reduced training time. The code is released at https://github.com/LowLevelAI/LITA-GS.

cs.CV↗

arXiv2025

Multimodal Image Matching based on Frequency-domain Information of Local Energy Response

Complicated nonlinear intensity differences, nonlinear local geometric distortions, noises and rotation transformation are main challenges in multimodal image matching. In order to solve these problems, we propose a method based on Frequency-domain Information of Local Energy Response called FILER. The core of FILER is the local energy response model based on frequency-domain information, which can overcome the effect of nonlinear intensity differences. To improve the robustness to local nonlinear geometric distortions and noises, we design a new edge structure enhanced feature detector and convolutional feature weighted descriptor, respectively. In addition, FILER overcomes the sensitivity of the frequency-domain information to the rotation angle and achieves rotation invariance. Extensive experiments multimodal image pairs show that FILER outperforms other state-of-the-art algorithms and has good robustness and universality.

cs.CV↗

arXiv2025

Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction

Self-supervised learning for computer vision has achieved tremendous progress and improved many downstream vision tasks such as image classification, semantic segmentation, and object detection. Among these, generative self-supervised vision learning approaches such as MAE and BEiT show promising performance. However, their global masked reconstruction mechanism is computationally demanding. To address this issue, we propose local masked reconstruction (LoMaR), a simple yet effective approach that performs masked reconstruction within a small window of 7$\times$7 patches on a simple Transformer encoder, improving the trade-off between efficiency and accuracy compared to global masked reconstruction over the entire image. Extensive experiments show that LoMaR reaches 84.1% top-1 accuracy on ImageNet-1K classification, outperforming MAE by 0.5%. After finetuning the pretrained LoMaR on 384$\times$384 images, it can reach 85.4% top-1 accuracy, surpassing MAE by 0.6%. On MS COCO, LoMaR outperforms MAE by 0.5 $\text{AP}^\text{box}$ on object detection and 0.5 $\text{AP}^\text{mask}$ on instance segmentation. LoMaR is especially more computation-efficient on pretraining high-resolution images, e.g., it is 3.1$\times$ faster than MAE with 0.2% higher classification accuracy on pretraining 448$\times$448 images. This local masked reconstruction learning mechanism can be easily integrated into any other generative self-supervised learning approach. Our code is publicly available in https://github.com/junchen14/LoMaR.

cs.CV↗

arXiv2025

4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding

Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities. However, there are no publicly standardized benchmarks to assess the abilities of MLLMs in understanding the 4D objects (3D objects with temporal evolution over time). In this paper, we introduce 4D-Bench, the first benchmark to evaluate the capabilities of MLLMs in 4D object understanding, featuring tasks in 4D object Question Answering (4D object QA) and 4D object captioning. 4D-Bench provides 4D objects with diverse categories, high-quality annotations, and tasks necessitating multi-view spatial-temporal understanding, different from existing 2D image/video-based benchmarks. With 4D-Bench, we evaluate a wide range of open-source and closed-source MLLMs. The results from the 4D object captioning experiment indicate that MLLMs generally exhibit weaker temporal understanding compared to their appearance understanding, notably, while open-source models approach closed-source performance in appearance understanding, they show larger performance gaps in temporal understanding. 4D object QA yields surprising findings: even with simple single-object videos, MLLMs perform poorly, with state-of-the-art GPT-4o achieving only 63\% accuracy compared to the human baseline of 91\%. These findings highlight a substantial gap in 4D object understanding and the need for further advancements in MLLMs.

cs.CV↗

arXiv2025

Rate-Distortion-Perception Tradeoff for Gaussian Vector Sources

This paper studies the rate-distortion-perception (RDP) tradeoff for a Gaussian vector source coding problem where the goal is to compress the multi-component source subject to distortion and perception constraints. Specifically, the RDP setting with either the Kullback-Leibler (KL) divergence or Wasserstein-2 metric as the perception loss function is examined, and it is shown that for Gaussian vector sources, jointly Gaussian reconstructions are optimal. We further demonstrate that the optimal tradeoff can be expressed as an optimization problem, which can be explicitly solved. An interesting property of the optimal solution is as follows. Without the perception constraint, the traditional reverse water-filling solution for characterizing the rate-distortion (RD) tradeoff of a Gaussian vector source states that the optimal rate allocated to each component depends on a constant, called the water level. If the variance of a specific component is below the water level, it is assigned a zero compression rate. However, with active distortion and perception constraints, we show that the optimal rates allocated to the different components are always positive. Moreover, the water levels that determine the optimal rate allocation for different components are unequal. We further treat the special case of perceptually perfect reconstruction and study its RDP function in the high-distortion and low-distortion regimes to obtain insight to the structure of the optimal solution.

cs.IT↗

arXiv2025

Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices

Optimal transport has found widespread applications in signal processing and machine learning. Among its many equivalent formulations, optimal transport seeks to reconstruct a random variable/vector with a prescribed distribution at the destination while minimizing the expected distortion relative to a given random variable/vector at the source. However, in practice, certain constraints may render the optimal transport plan infeasible. In this work, we consider three types of constraints: rate constraints, dimension constraints, and channel constraints, motivated by perception-aware lossy compression, generative principal component analysis, and deep joint source-channel coding, respectively. Special attenion is given to the setting termed Gaussian Wasserstein optimal transport, where both the source and reconstruction variables are multivariate Gaussian, and the end-to-end distortion is measured by the mean squared error. We derive explicit results for the minimum achievable mean squared error under the three aforementioned constraints when the covariance matrices of the source and reconstruction variables commute.

cs.IT↗

arXiv2025

Electromagnetic responses of a non-extensive quark-gluon plasma

Based on the non-extensive statistical mechanics and the gluon polarization tensor obtained from kinetic theory, we derive the longitudinal and transverse gluon self-energies for the quark-gluon plasma. The electric permittivity $\varepsilon$ and the magnetic permeability $μ_M$ are evaluated from the gluon self-energies through which the real part of the square of the refraction index ${\rm Re}\, n^2$ and the Depine-Lakhtakia index $n_{DL}$ are investigated. The real part of $\varepsilon$ displays a frequency pole $ω_d=p$, which is just the position of the frequency inflexion of the imaginary part of $\varepsilon$. The non-extensive parameter $q$ significantly affects the real and imaginary parts of $\varepsilon$ in the space-like region $ω<p$, while the frequency pole $ω_d=p$ remains unchanged as $q$ increases. The magnetic permeability, ${\rm Re}\, n^2$ and the Depine-Lakhtakia index $n_{DL}$ diverge at frequency $ω_m$. As $q$ increases, the pole frequency $ω_m$ shifts to large frequency region. The Depine-Lakhtakia index $n_{DL}$ becomes negative in a quite large frequency region $ω\in[ω_c, ω_m]$. When $q$ increases, the frequency range for $n_{DL}<0$ becomes wider. Nevertheless, there are no propagating modes for the negative refraction. In addition, as momentum $p$ increases, the electric permittivity, the magnetic permeability, ${\rm Re}\, n^2$ and $n_{DL}$ are sensitive to the change of $p$, which indicates the importance of the spatial dispersion in the electromagnetic responses of the QGP.

hep-ph↗

arXiv2025

Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning

Neural network quantization is a very promising solution in the field of model compression, but its resulting accuracy highly depends on a training/fine-tuning process and requires the original data. This not only brings heavy computation and time costs but also is not conducive to privacy and sensitive information protection. Therefore, a few recent works are starting to focus on data-free quantization. However, data-free quantization does not perform well while dealing with ultra-low precision quantization. Although researchers utilize generative methods of synthetic data to address this problem partially, data synthesis needs to take a lot of computation and time. In this paper, we propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process. By assuming the quantized error caused by a low-precision quantized layer can be restored via the reconstruction of a high-precision quantized layer, we mathematically formulate the reconstruction loss between the pre-trained full-precision model and its layer-wise mixed-precision quantized model. Based on our formulation, we theoretically deduce the closed-form solution by minimizing the reconstruction loss of the feature maps. Since DF-MPC does not require any original/synthetic data, it is a more efficient method to approximate the full-precision model. Experimentally, our DF-MPC is able to achieve higher accuracy for an ultra-low precision quantized model compared to the recent methods without any data and fine-tuning process.

cs.LG↗

arXiv2025

On Self-Adaptive Perception Loss Function for Sequential Lossy Compression

We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. As the main contribution, we propose and analyze a new PLF that considers the joint distribution between the current source frame and the previous reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. From a qualitative perspective, the proposed metric can simultaneously avoid the error-permanence phenomenon and also better exploit the temporal correlation between high-quality reconstructions. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames. We provide a detailed comparison of the proposed perception loss function with previous approaches through both information theoretic analysis as well as experiments involving moving MNIST and UVG datasets.

cs.LG↗

arXiv2025

On the Fundamental Limits of Integrated Sensing and Communications Under Logarithmic Loss

We study a unified information-theoretic framework for integrated sensing and communications (ISAC), applicable to both monostatic and bistatic sensing scenarios. Special attention is given to the case where the sensing receiver (Rx) is required to produce a "soft" estimate of the state sequence, with logarithmic loss serving as the performance metric. We derive lower and upper bounds on the capacity-distortion function, which delineates the fundamental tradeoff between communication rate and sensing distortion. These bounds coincide when the channel between the ISAC transmitter (Tx) and the communication Rx is degraded with respect to the channel between the ISAC Tx and the sensing Rx, or vice versa. Furthermore, we provide a complete characterization of the capacity-distortion function for an ISAC system that simultaneously transmits information over a binary-symmetric channel and senses additive Bernoulli states through another binary-symmetric channel. The Gaussian counterpart of this problem is also explored, which, together with a state-splitting trick, fully determines the capacity-distortion-power function under the squared error distortion measure.

cs.IT↗