arXiv subjects

Fan Zhang

Publications and source records attributed to Fan Zhang.

At least 451 records · Page 25Linked to original sources

arXiv2024

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hinges on the availability of high-quality image-text datasets that offer diverse visual elements and throughout image descriptions. However, the scarcity of such hyper-detailed datasets currently hinders progress within the MLLM community. The bottleneck stems from the limited perceptual capabilities of current caption engines, which fall short in providing complete and accurate annotations. To facilitate the cutting-edge research of MLLMs on comprehensive vision perception, we thereby propose Perceptual Fusion, using a low-budget but highly effective caption engine for complete and accurate image descriptions. Specifically, Perceptual Fusion integrates diverse perception experts as image priors to provide explicit information on visual elements and adopts an efficient MLLM as a centric pivot to mimic advanced MLLMs' perception abilities. We carefully select 1M highly representative images from uncurated LAION dataset and generate dense descriptions using our engine, dubbed DenseFusion-1M. Extensive experiments validate that our engine outperforms its counterparts, where the resulting dataset significantly improves the perception and cognition abilities of existing MLLMs across diverse vision-language benchmarks, especially with high-resolution images as inputs. The dataset and code are publicly available at https://github.com/baaivision/DenseFusion.

cs.CV↗

arXiv2024

DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2

Speech-driven gesture generation using transformer-based generative models represents a rapidly advancing area within virtual human creation. However, existing models face significant challenges due to their quadratic time and space complexities, limiting scalability and efficiency. To address these limitations, we introduce DiM-Gestor, an innovative end-to-end generative model leveraging the Mamba-2 architecture. DiM-Gestor features a dual-component framework: (1) a fuzzy feature extractor and (2) a speech-to-gesture mapping module, both built on the Mamba-2. The fuzzy feature extractor, integrated with a Chinese Pre-trained Model and Mamba-2, autonomously extracts implicit, continuous speech features. These features are synthesized into a unified latent representation and then processed by the speech-to-gesture mapping module. This module employs an Adaptive Layer Normalization (AdaLN)-enhanced Mamba-2 mechanism to uniformly apply transformations across all sequence tokens. This enables precise modeling of the nuanced interplay between speech features and gesture dynamics. We utilize a diffusion model to train and infer diverse gesture outputs. Extensive subjective and objective evaluations conducted on the newly released Chinese Co-Speech Gestures dataset corroborate the efficacy of our proposed model. Compared with Transformer-based architecture, the assessments reveal that our approach delivers competitive results and significantly reduces memory usage, approximately 2.4 times, and enhances inference speeds by 2 to 4 times. Additionally, we released the CCG dataset, a Chinese Co-Speech Gestures dataset, comprising 15.97 hours (six styles across five scenarios) of 3D full-body skeleton gesture motion performed by professional Chinese TV broadcasters.

cs.SD↗

arXiv2024

VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has several appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. 4) Versatile Benchmarking: VBench++ supports evaluating text-to-video and image-to-video. We introduce a high-quality Image Suite with an adaptive aspect ratio to enable fair evaluations across different image-to-video generation settings. Beyond assessing technical quality, VBench++ evaluates the trustworthiness of video generative models, providing a more holistic view of model performance. 5) Full Open-Sourcing: We fully open-source VBench++ and continually add new video generation models to our leaderboard to drive forward the field of video generation.

cs.CV↗

arXiv2024

RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content

Super-resolution (SR) is a key technique for improving the visual quality of video content by increasing its spatial resolution while reconstructing fine details. SR has been employed in many applications including video streaming, where compressed low-resolution content is typically transmitted to end users and then reconstructed with a higher resolution and enhanced quality. To support real-time playback, it is important to implement fast SR models while preserving reconstruction quality; however most existing solutions, in particular those based on complex deep neural networks, fail to do so. To address this issue, this paper proposes a low-complexity SR method, RTSR, designed to enhance the visual quality of compressed video content, focusing on resolution up-scaling from a) 360p to 1080p and from b) 540p to 4K. The proposed approach utilizes a CNN-based network architecture, which was optimized for AV1 (SVT)-encoded content at various quantization levels based on a dual-teacher knowledge distillation method. This method was submitted to the AIM 2024 Video Super-Resolution Challenge, specifically targeting the Efficient/Mobile Real-Time Video Super-Resolution competition. It achieved the best trade-off between complexity and coding performance (measured in PSNR, SSIM and VMAF) among all six submissions. The code will be available soon.

eess.IV↗

arXiv2024

Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events

Retrieval and recommendation are two essential tasks in modern search tools. This paper introduces a novel retrieval-reranking framework leveraging Large Language Models (LLMs) to enhance the spatiotemporal and semantic associated mining and recommendation of relevant unusual climate and environmental events described in news articles and web posts. This framework uses advanced natural language processing techniques to address the limitations of traditional manual curation methods in terms of high labor cost and lack of scalability. Specifically, we explore an optimized solution to employ cutting-edge embedding models for semantically analyzing spatiotemporal events (news) and propose a Geo-Time Re-ranking (GT-R) strategy that integrates multi-faceted criteria including spatial proximity, temporal association, semantic similarity, and category-instructed similarity to rank and identify similar spatiotemporal events. We apply the proposed framework to a dataset of four thousand Local Environmental Observer (LEO) Network events, achieving top performance in recommending similar events among multiple cutting-edge dense retrieval models. The search and recommendation pipeline can be applied to a wide range of similar data search tasks dealing with geospatial and temporal data. We hope that by linking relevant events, we can better aid the general public to gain an enhanced understanding of climate change and its impact on different communities.

cs.IR↗

arXiv2024

BVI-CR: A Multi-View Human Dataset for Volumetric Video Compression

The advances in immersive technologies and 3D reconstruction have enabled the creation of digital replicas of real-world objects and environments with fine details. These processes generate vast amounts of 3D data, requiring more efficient compression methods to satisfy the memory and bandwidth constraints associated with data storage and transmission. However, the development and validation of efficient 3D data compression methods are constrained by the lack of comprehensive and high-quality volumetric video datasets, which typically require much more effort to acquire and consume increased resources compared to 2D image and video databases. To bridge this gap, we present an open multi-view volumetric human dataset, denoted BVI-CR, which contains 18 multi-view RGB-D captures and their corresponding textured polygonal meshes, depicting a range of diverse human actions. Each video sequence contains 10 views in 1080p resolution with durations between 10-15 seconds at 30FPS. Using BVI-CR, we benchmarked three conventional and neural coordinate-based multi-view video compression methods, following the MPEG MIV Common Test Conditions, and reported their rate quality performance based on various quality metrics. The results show the great potential of neural representation based methods in volumetric video compression compared to conventional video coding methods (with an up to 38\% average coding gain in PSNR). This dataset provides a development and validation platform for a variety of tasks including volumetric reconstruction, compression, and quality assessment. The database will be shared publicly at \url{https://github.com/fan-aaron-zhang/bvi-cr}.

cs.CV↗

arXiv2024

MICCAI-CDMRI 2023 QuantConn Challenge Findings on Achieving Robust Quantitative Connectivity through Harmonized Preprocessing of Diffusion MRI

White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. There is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences.

physics.med-ph↗

arXiv2024

Disposable Opto-Acoustic Window Enabled Cost-effective Photoacoustic-Ultrasound Dual-modal Imaging

Photoacoustic imaging (PAI) and ultrasound imaging (USI) are important biomedical imaging techniques, due to their unique and complementary advantages in tissue's structure and function visualization. In this Letter, we proposed a coaxial photoacoustic-ultrasound dual-modal imaging system (coPAUS) with disposable opto-acoustic window. This opto-acoustic window allows part of light to go through it, and another part of light to be converted to ultrasound transmission signal by photoacoustic effect. By single laser pulse illumination, both PA signals and reflected US signals can be generated. Then, a linear array probe receives both PA and US signals, enabling simultaneous dual-modal PA and US imaging. Ex vivo experiments were conducted involving pencil lead, hair, and plastic tube with black spot, as well as in vivo experiment on human finger. The system's resolutions for PA and US imaging are 215 um and 91.125 um, with signal-to-noise ratios for PA and US signals reached up to 37.48 dB and 29.75 dB, respectively, proving the feasibility of the coPAUS dual-modal imaging. The proposed coPAUS system with disposable opto-acoustic window provides an immediate and cost-effective approach to enable US imaging capability based on an existing PA imaging system.

physics.med-ph↗

arXiv2024

DualDn: Dual-domain Denoising via Differentiable ISP

Image denoising is a critical component in a camera's Image Signal Processing (ISP) pipeline. There are two typical ways to inject a denoiser into the ISP pipeline: applying a denoiser directly to captured raw frames (raw domain) or to the ISP's output sRGB images (sRGB domain). However, both approaches have their limitations. Residual noise from raw-domain denoising can be amplified by the subsequent ISP processing, and the sRGB domain struggles to handle spatially varying noise since it only sees noise distorted by the ISP. Consequently, most raw or sRGB domain denoising works only for specific noise distributions and ISP configurations. To address these challenges, we propose DualDn, a novel learning-based dual-domain denoising. Unlike previous single-domain denoising, DualDn consists of two denoising networks: one in the raw domain and one in the sRGB domain. The raw domain denoising adapts to sensor-specific noise as well as spatially varying noise levels, while the sRGB domain denoising adapts to ISP variations and removes residual noise amplified by the ISP. Both denoising networks are connected with a differentiable ISP, which is trained end-to-end and discarded during the inference stage. With this design, DualDn achieves greater generalizability compared to most learning-based denoising methods, as it can adapt to different unseen noises, ISP parameters, and even novel ISP pipelines. Experiments show that DualDn achieves state-of-the-art performance and can adapt to different denoising architectures. Moreover, DualDn can be used as a plug-and-play denoising module with real cameras without retraining, and still demonstrate better performance than commercial on-camera denoising. The project website is available at: https://openimaginglab.github.io/DualDn/

eess.IV↗

arXiv2024

AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection

Image Signal Processors (ISPs) convert raw sensor signals into digital images, which significantly influence the image quality and the performance of downstream computer vision tasks. Designing ISP pipeline and tuning ISP parameters are two key steps for building an imaging and vision system. To find optimal ISP configurations, recent works use deep neural networks as a proxy to search for ISP parameters or ISP pipelines. However, these methods are primarily designed to maximize the image quality, which are sub-optimal in the performance of high-level computer vision tasks such as detection, recognition, and tracking. Moreover, after training, the learned ISP pipelines are mostly fixed at the inference time, whose performance degrades in dynamic scenes. To jointly optimize ISP structures and parameters, we propose AdaptiveISP, a task-driven and scene-adaptive ISP. One key observation is that for the majority of input images, only a few processing modules are needed to improve the performance of downstream recognition tasks, and only a few inputs require more processing. Based on this, AdaptiveISP utilizes deep reinforcement learning to automatically generate an optimal ISP pipeline and the associated ISP parameters to maximize the detection performance. Experimental results show that AdaptiveISP not only surpasses the prior state-of-the-art methods for object detection but also dynamically manages the trade-off between detection performance and computational cost, especially suitable for scenes with large dynamic range variations. Project website: https://openimaginglab.github.io/AdaptiveISP/.

cs.CV↗

arXiv2024

Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation

Medical image segmentation poses challenges due to domain gaps, data modality variations, and dependency on domain knowledge or experts, especially for low- and middle-income countries (LMICs). Whereas for humans, given a few exemplars (with corresponding labels), we are able to segment different medical images even without exten-sive domain-specific clinical training. In addition, current SAM-based medical segmentation models use fine-grained visual prompts, such as the bounding rectangle generated from manually annotated target segmentation mask, as the bounding box (bbox) prompt during the testing phase. However, in actual clinical scenarios, no such precise prior knowledge is available. Our experimental results also reveal that previous models nearly fail to predict when given coarser bbox prompts. Considering these issues, in this paper, we introduce a domain-aware selective adaptation approach to adapt the general knowledge learned from a large model trained with natural images to the corresponding medical domains/modalities, with access to only a few (e.g. less than 5) exemplars. Our method mitigates the aforementioned limitations, providing an efficient and LMICs-friendly solution. Extensive experimental analysis showcases the effectiveness of our approach, offering potential advancements in healthcare diagnostics and clinical applications in LMICs.

cs.CV↗

arXiv2024

RediSwap: MEV Redistribution Mechanism for CFMMs

Automated Market Makers (AMMs) are essential to decentralized finance, offering continuous liquidity and enabling intermediary-free trading on blockchains. However, participants in AMMs are vulnerable to Maximal Extractable Value (MEV) exploitation. Users face threats such as front-running, back-running, and sandwich attacks, while liquidity providers (LPs) incur the loss-versus-rebalancing (LVR). In this paper, we introduce RediSwap, a novel AMM designed to capture MEV at the application level and refund it fairly among users and liquidity providers. At its core, RediSwap features an MEV-redistribution mechanism that manages arbitrage opportunities within the AMM pool. We formalize the mechanism design problem and the desired game-theoretical properties. A central insight underpinning our mechanism is the interpretation of the maximal MEV value as the sum of LVR and individual user losses. We prove that our mechanism is incentive-compatible and Sybil-proof, and demonstrate that it is easy for arbitrageurs to participate. We empirically compared RediSwap with existing solutions by replaying historical AMM trades. Our results suggest that RediSwap can achieve better execution than UniswapX in 89% of trades and reduce LPs' loss to under 0.5% of the original LVR in most cases.

cs.GT↗

arXiv2024

BVI-AOM: A New Training Dataset for Deep Video Compression Optimization

Deep learning is now playing an important role in enhancing the performance of conventional hybrid video codecs. These learning-based methods typically require diverse and representative training material for optimization in order to achieve model generalization and optimal coding performance. However, existing datasets either offer limited content variability or come with restricted licensing terms constraining their use to research purposes only. To address these issues, we propose a new training dataset, named BVI-AOM, which contains 956 uncompressed sequences at various resolutions from 270p to 2160p, covering a wide range of content and texture types. The dataset comes with more flexible licensing terms and offers competitive performance when used as a training set for optimizing deep video coding tools. The experimental results demonstrate that when used as a training set to optimize two popular network architectures for two different coding tools, the proposed dataset leads to additional bitrate savings of up to 0.29 and 2.98 percentage points in terms of PSNR-Y and VMAF, respectively, compared to an existing training dataset, BVI-DVC, which has been widely used for deep video coding. The BVI-AOM dataset is available at https://github.com/fan-aaron-zhang/bvi-aom

eess.IV↗

arXiv2024

Signatures of sliding Wigner crystals in bilayer graphene at zero and finite magnetic fields

AB-stacked bilayer graphene has emerged as a fascinating yet simple platform for exploring macroscopic quantum phenomena of correlated electrons. Unexpectedly, a phase with negative dR/dT has recently been observed when a large electric displacement field is applied and the charge carrier density is tuned to the vicinity of an ultra-low-density van Hove singularity. This phase exhibits features consistent with Wigner crystallization, including a characteristic temperature dependence and non-linear current bias behavior. However, more direct evidence for the emergence of an electron crystal in AB-stacked bilayer graphene at zero magnetic field remains elusive. Here we explore the low-frequency noise consistent with depinning and sliding of a Wigner crystal lattice. The current bias and frequency dependence of these noise spectra align well with findings from previous experimental and theoretical studies on the quantum electron solids. Our results offer transport signatures consistent with Wigner crystallization in AB-stacked bilayer graphene at zero and finite magnetic fields, paving the way for further substantiating an anomalous Hall crystal in its original form.

cond-mat.mes-hall↗

arXiv2024

Self-consistent theory for the fractional quantum anomalous Hall effect in rhombohedral pentalayer graphene

The fractional quantum anomalous Hall (FQAH) effect in rhombohedral pentalayer graphene (PLG) has attracted significant attention due to its potential for observing exotic quantum states. In this work, we present a self-consistent Hartree-Fock theory for the FQAH effect in rhombohedral PLG. In particular, we focus on the convergence of the Hartree-Fock calculation with various reference fields and discuss the stability of the FQAH states in PLG. We show that the so-called charge neutrality scheme provides an unambiguous result for the Hartree-Fock calculation, as it ensures a convergence with respect to the momentum cutoff. Based on the Hartree-Fock band structure, we further carry out exact diagonalization calculations to explore the stability of the FQAH states in PLG. Our work provides an improved and unified (minimal) theoretical framework to understand the FQAH effect in rhombohedral PLG and paves the way for future experimental and theoretical studies.

cond-mat.str-el↗

arXiv2024

Resolution Enhancement of Under-sampled Photoacoustic Microscopy Images using Implicit Neural Representations

Acoustic-Resolution Photoacoustic Microscopy (AR-PAM) is promising for subcutaneous vascular imaging, but its spatial resolution is constrained by the Point Spread Function (PSF). Traditional deconvolution methods like Richardson-Lucy and model-based deconvolution use the PSF to improve resolution. However, accurately measuring the PSF is difficult, leading to reliance on less accurate blind deconvolution techniques. Additionally, AR-PAM suffers from long scanning times, which can be reduced via down-sampling, but this necessitates effective image recovery from under-sampled data, a task where traditional interpolation methods fall short, particularly at high under-sampling rates. To address these challenges, we propose an approach based on Implicit Neural Representations (INR). This method learns a continuous mapping from spatial coordinates to initial acoustic pressure, overcoming the limitations of discrete imaging and enhancing AR-PAM's resolution. By treating the PSF as a learnable parameter within the INR framework, our technique mitigates inaccuracies associated with PSF estimation. We evaluated our method on simulated vascular data, showing significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) over conventional methods. Qualitative enhancements were also observed in leaf vein and in vivo mouse brain microvasculature images. When applied to a custom AR-PAM system, experiments with pencil lead demonstrated that our method delivers sharper, higher-resolution results, indicating its potential to advance photoacoustic microscopy.

cs.CV↗

arXiv2024

RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content

With recent advances in deep learning, numerous algorithms have been developed to enhance video quality, reduce visual artifacts, and improve perceptual quality. However, little research has been reported on the quality assessment of enhanced content - the evaluation of enhancement methods is often based on quality metrics that were designed for compression applications. In this paper, we propose a novel blind deep video quality assessment (VQA) method specifically for enhanced video content. It employs a new Recurrent Memory Transformer (RMT) based network architecture to obtain video quality representations, which is optimized through a novel content-quality-aware contrastive learning strategy based on a new database containing 13K training patches with enhanced content. The extracted quality representations are then combined through linear regression to generate video-level quality indices. The proposed method, RMT-BVQA, has been evaluated on the VDPVE (VQA Dataset for Perceptual Video Enhancement) database through a five-fold cross validation. The results show its superior correlation performance when compared to ten existing no-reference quality metrics.

eess.IV↗

arXiv2024

Emu3: Next-Token Prediction is All You Need

While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.g., CLIP combined with LLMs). In this paper, we introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences. Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship models such as SDXL and LLaVA-1.6, while eliminating the need for diffusion or compositional architectures. Emu3 is also capable of generating high-fidelity video via predicting the next token in a video sequence. We simplify complex multimodal model designs by converging on a singular focus: tokens, unlocking great potential for scaling both during training and inference. Our results demonstrate that next-token prediction is a promising path towards building general multimodal intelligence beyond language. We open-source key techniques and models to support further research in this direction.

cs.CV↗