arXiv subjects

Kin-Man Lam

Publications and source records attributed to Kin-Man Lam.

At least 19 recordsLinked to original sources

arXiv2026

AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audio-video generation is challenging. Heterogeneous multimodal rewards entangle learning signals and complicate credit assignment. Joint optimization of two modality towers is computationally expensive given their divergent dynamics. Moreover, synchronization evaluation difficulty depends on paired samples, preventing fair reward comparisons. We propose AV-GRPO, a modality-anchored online diffusion RL framework, and 5DAV, a decoupled, difficulty-controllable training dataset. AV-GRPO includes three key modules: (1) modality-anchored rollouts to disentangle learning signals and stabilize difficulty; (2) trajectory-locked frozen-tower optimization to reduce cost and reassign credit; (3) adaptive objectives and perturbation strengths tailored to modality-specific dynamics. This converts coupled multimodal preference learning into unimodal subproblems for precise reward attribution and better synchronization. Our 5DAV dataset decouples samples across five dimensions for systematic training. Experiments on JavisBench and VABench demonstrate AV-GRPO outperforms LTX-2.3 in generation quality, semantic alignment and cross-modal synchronization under LoRA and full fine-tuning. Ablations confirm our designs. Code and data: https://github.com/zhiyuxu03/AV-GRPO

cs.CV↗

arXiv2026

Bidirectional Cross-frequency Domain Interaction Network for UHD Low-Light Image Enhancement

Existing Ultra-High-Definition (UHD) low-light image enhancement (LLIE) methods typically rely on either spatial- or frequency-domain modeling, or independently process different frequency components for efficient restoration. However, they often fail to jointly exploit complementary spatial--frequency information and the inherent relationship between illumination and structural information across frequencies, leading to inconsistent illumination, residual noise, and detail artifacts. In this paper, we propose a novel Bidirectional Cross-frequency Domain Interaction Network (BiFreqNet) for UHD LLIE. Specifically, BiFreqNet incorporates a Dual-domain Feature Interaction (DFI) module into the multi-scale representations of a pretrained variational autoencoder (VAE) to perform reciprocal enhancement between low- and high-frequency features. DFI consists of a Spatial and Spectral-Aware Low-Frequency Enhancement (S$^2$LFE) block and a Cross-Frequency Enhancement (CFE) block. S$^2$LFE exploits high-frequency structural cues to guide low-frequency restoration and jointly models spatial and spectral information to recover global exposure and spatially varying illumination while suppressing sensor noise. CFE further leverages the enhanced low-frequency contextual information to guide adaptive high-frequency refinement, enabling faithful reconstruction of structures and fine details. Extensive experiments on four general and UHD LLIE benchmarks demonstrate that BiFreqNet achieves competitive or superior performance compared with state-of-the-art methods.

cs.CV↗

arXiv2026

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.

cs.CV↗

arXiv2026

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning

Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept. SpecT-OT introduces a Spectral Reparameterization Projector (SRP), which parameterizes projector weights with fixed Fourier bases and learnable coefficients to improve the modeling of rapidly varying discriminative features, and Temporal Affinity Regularization (TAR), which imposes distance-aware, label-free constraints on pairwise frame affinities to stabilize local temporal structure. The two components jointly produce more discriminative and temporally stable transport costs, yielding more reliable pseudo-labels for iterative representation learning. Experiments on four benchmarks demonstrate strong performance compared with state-of-the-art methods. SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly, respectively.

cs.CV↗

arXiv2026

Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal

Adverse weather causes diverse and complex image degradations, severely compromising the reliability of computer vision systems. Existing all-in-one restoration models attempt to address multiple degradation types within a unified framework, but often lack explicit spatial and semantic modeling of degradation characteristics, limiting their adaptability to diverse weather conditions. To address this limitation, we propose a Degradation-Aware Cross-Modal Prompt Compensation Network (DCMPC-Net) that leverages cross-modal degradation cues from a pretrained vision-language model to condition restoration features within a unified backbone. Specifically, our DCMPC-Net mainly consists of the Cross-Modal Prompt Generator (CMPG), Prompt-Guided Attention Alignment Module (PGAAM), and Dual Feature Compensation Module (DFCM). The CMPG integrates textual embeddings with visual features to produce degradation-aware prompts that encode degradation-related semantic and contextual cues. These prompts are injected into the decoder via a PGAAM, which adaptively aligns semantic information with degraded regions to facilitate context-aware restoration. To further enhance structural fidelity, DFCM is introduced that disentangles degradation artifacts from scene structures, thereby improving the reconstruction of fine textures and detailed content. By integrating cross-modal semantic guidance with spatial alignment and structural enhancement, DCMPC-Net achieves robust and perceptually consistent restoration across diverse weather conditions. Extensive experiments show that DCMPC-Net outperforms state-of-the-art methods in both task-specific and unified settings, achieving superior accuracy and visual fidelity.

cs.CV↗

arXiv2026

Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator

Image cropping aims to improve image aesthetics by preserving important content within an appropriately composed region. However, most existing methods focus primarily on salient regions and therefore have limited sensitivity to the global relationships among the main image components. To address this limitation, we propose Global Attention-Fused Image Cropping (GAFIC), which consists of an Attention-Guided Feature Fusion (AGFF) and a Global-Aligned Crop Evaluator (GACE). AGFF aggregates the importance of local regions to construct a global representation that captures both image structure and local details. GACE aligns candidate crop features with this global representation, enabling crop evaluation to remain sensitive to boundary changes. We further combine three ranking losses across multiple scales to obtain accurate and stable crop scores. Extensive experiments on the GAIC and CPC datasets demonstrate that GAFIC outperforms existing image-cropping methods, particularly in terms of accuracy and stability. Unlike pixel-level retargeting methods such as seam carving, inpainting, and diffusion-based synthesis, GAFIC does not synthesize or modify the retained pixels; instead, it selects an aesthetically preferred crop from the source image, making it suitable for scenarios where pixel integrity and efficient batch processing are important. The source code is available at https://github.com/AIVRC/GAFIC.git.

cs.CV↗

arXiv2026

Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition

Facial Expression Recognition (FER) is essential for human-machine interaction, as it enables machines to interpret human emotions and internal states from facial affective behaviors. Although deep learning has significantly advanced FER performance, most existing deep-learning-based FER methods rely heavily on discriminative classifiers for fast predictions. These models tend to learn shortcuts and are vulnerable to even minor distribution shifts. To address this issue, we adopt a conditional generative diffusion model and introduce the Emotion Diffusion Classifier (EmoDC) for FER, which demonstrates enhanced adversarial robustness. However, retraining EmoDC using standard strategies fails to penalize incorrect categorical descriptions, leading to suboptimal recognition performance. To improve EmoDC, we propose margin-based discrepancy training, which encourages accurate predictions when conditioned on correct categorical descriptions and penalizes predictions conditioned on mismatched ones. This method enforces a minimum margin between noise-prediction errors for correct and incorrect categories, thereby enhancing the model's discriminative capability. Nevertheless, using a fixed margin fails to account for the varying difficulty of noise prediction across different images, limiting its effectiveness. To overcome this limitation, we propose Adaptive Margin Discrepancy Training (AMDiT), which dynamically adjusts the margin for each sample. Extensive experiments show that AMDiT significantly improves the accuracy of EmoDC over the baseline model with standard denoising diffusion training under 100-step evaluations. Additionally, AMDiT-enhanced EmoDC has better generalization and robustness than state-of-the-art discriminative classifiers.

cs.CV↗

arXiv2025

Vision-Language Model Guided Image Restoration

Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the visual and linguistic knowledge. Recent efforts have attempted to incorporate Vision-language models (VLMs), which excel at aligning visual and textual features, into universal IR. Nevertheless, these methods fail to utilize the linguistic priors to ensure semantic coherence during the restoration process. To address this issue, in this paper, we propose the Vision-Language Model Guided Image Restoration (VLMIR) framework, which leverages the rich vision-language priors of VLMs, such as CLIP, to enhance IR performance through improved visual perception and semantic understanding. Our approach consists of two stages: VLM-based feature extraction and diffusion-based image restoration. In the first stage, we extract complementary visual and linguistic representations of input images by condensing the visual perception and high-level semantic priors through VLMs. Specifically, we align the embeddings of captions from low-quality and high-quality images using a cosine similarity loss with LoRA fine-tuning, and employ a degradation predictor to decompose degradation and clean image content embeddings. These complementary visual and textual embeddings are then integrated into a diffusion-based model via cross-attention mechanisms for enhanced restoration. Extensive experiments and ablation studies demonstrate that VLMIR achieves superior performance across both universal and degradation-specific IR tasks, underscoring the critical role of integrated visual and linguistic knowledge from VLMs in advancing image restoration capabilities.

cs.CV↗

arXiv2025

Multi-level distortion-aware deformable network for omnidirectional image super-resolution

As augmented reality and virtual reality applications gain popularity, image processing for OmniDirectional Images (ODIs) has attracted increasing attention. OmniDirectional Image Super-Resolution (ODISR) is a promising technique for enhancing the visual quality of ODIs. Before performing super-resolution, ODIs are typically projected from a spherical surface onto a plane using EquiRectangular Projection (ERP). This projection introduces latitude-dependent geometric distortion in ERP images: distortion is minimal near the equator but becomes severe toward the poles, where image content is stretched across a wider area. However, existing ODISR methods have limited sampling ranges and feature extraction capabilities, which hinder their ability to capture distorted patterns over large areas. To address this issue, we propose a novel Multi-level Distortion-aware Deformable Network (MDDN) for ODISR, designed to expand the sampling range and receptive field. Specifically, the feature extractor in MDDN comprises three parallel branches: a deformable attention mechanism (serving as the dilation=1 path) and two dilated deformable convolutions with dilation rates of 2 and 3. This architecture expands the sampling range to include more distorted patterns across wider areas, generating dense and comprehensive features that effectively capture geometric distortions in ERP images. The representations extracted from these deformable feature extractors are adaptively fused in a multi-level feature fusion module. Furthermore, to reduce computational cost, a low-rank decomposition strategy is applied to dilated deformable convolutions. Extensive experiments on publicly available datasets demonstrate that MDDN outperforms state-of-the-art methods, underscoring its effectiveness and superiority in ODISR.

cs.CV↗

arXiv2025

SA$^{2}$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging

Spine segmentation, based on ultrasound volume projection imaging (VPI), plays a vital role for intelligent scoliosis diagnosis in clinical applications. However, this task faces several significant challenges. Firstly, the global contextual knowledge of spines may not be well-learned if we neglect the high spatial correlation of different bone features. Secondly, the spine bones contain rich structural knowledge regarding their shapes and positions, which deserves to be encoded into the segmentation process. To address these challenges, we propose a novel scale-adaptive structure-aware network (SA$^{2}$Net) for effective spine segmentation. First, we propose a scale-adaptive complementary strategy to learn the cross-dimensional long-distance correlation features for spinal images. Second, motivated by the consistency between multi-head self-attention in Transformers and semantic level affinity, we propose structure-affinity transformation to transform semantic features with class-specific affinity and combine it with a Transformer decoder for structure-aware reasoning. In addition, we adopt a feature mixing loss aggregation method to enhance model training. This method improves the robustness and accuracy of the segmentation process. The experimental results demonstrate that our SA$^{2}$Net achieves superior segmentation performance compared to other state-of-the-art methods. Moreover, the adaptability of SA$^{2}$Net to various backbones enhances its potential as a promising tool for advanced scoliosis diagnosis using intelligent spinal image analysis. The code and experimental demo are available at https://github.com/taetiseo09/SA2Net.

cs.CV↗

arXiv2025

Enhancing Technical Documents Retrieval for RAG

In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of understanding and retrieving complex technical content by leveraging the capabilities of Large Language Models (LLMs). First, we enhance user queries by generating expanded representations that better capture user intent and improve dataset diversity, thereby enriching the fine-tuning process for embedding models. Second, we apply summary extraction techniques to encode essential contextual information, refining the representation of technical documents. To further enhance retrieval performance, we fine-tune a bi-encoder BERT model using soft prompting, incorporating separate learning parameters for queries and document context to capture fine-grained semantic nuances. We evaluate our approach on two public datasets, RAG-EDA and Rust-Docs-QA, demonstrating that Technical-Embeddings significantly outperforms baseline models in both precision and recall. Our findings highlight the effectiveness of integrating query expansion and contextual summarization to enhance information access and comprehension in technical domains. This work advances the state of Retrieval-Augmented Generation (RAG) systems, offering new avenues for efficient and accurate technical document retrieval in engineering and product development workflows.

cs.IR↗

arXiv2025

Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework

3D Gaussian Splatting (3DGS) has demonstrated remarkable real-time performance in novel view synthesis, yet its effectiveness relies heavily on dense multi-view inputs with precisely known camera poses, which are rarely available in real-world scenarios. When input views become extremely sparse, the Structure-from-Motion (SfM) method that 3DGS depends on for initialization fails to accurately reconstruct the 3D geometric structures of scenes, resulting in degraded rendering quality. In this paper, we propose a novel SfM-free 3DGS-based method that jointly estimates camera poses and reconstructs 3D scenes from extremely sparse-view inputs. Specifically, instead of SfM, we propose a dense stereo module to progressively estimates camera pose information and reconstructs a global dense point cloud for initialization. To address the inherent problem of information scarcity in extremely sparse-view settings, we propose a coherent view interpolation module that interpolates camera poses based on training view pairs and generates viewpoint-consistent content as additional supervision signals for training. Furthermore, we introduce multi-scale Laplacian consistent regularization and adaptive spatial-aware multi-scale geometry regularization to enhance the quality of geometrical structures and rendered content. Experiments show that our method significantly outperforms other state-of-the-art 3DGS-based approaches, achieving a remarkable 2.75dB improvement in PSNR under extremely sparse-view conditions (using only 2 training views). The images synthesized by our method exhibit minimal distortion while preserving rich high-frequency details, resulting in superior visual quality compared to existing techniques.

cs.CV↗

arXiv2025

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Vision-Language Models (VLMs) extend the capabilities of Large Language Models (LLMs) by incorporating visual information, yet they remain vulnerable to jailbreak attacks, especially when processing noisy or corrupted images. Although existing VLMs adopt security measures during training to mitigate such attacks, vulnerabilities associated with noise-augmented visual inputs are overlooked. In this work, we identify that missing noise-augmented training causes critical security gaps: many VLMs are susceptible to even simple perturbations such as Gaussian noise. To address this challenge, we propose Robust-VLGuard, a multimodal safety dataset with aligned / misaligned image-text pairs, combined with noise-augmented fine-tuning that reduces attack success rates while preserving functionality of VLM. For stronger optimization-based visual perturbation attacks, we propose DiffPure-VLM, leveraging diffusion models to convert adversarial perturbations into Gaussian-like noise, which can be defended by VLMs with noise-augmented safety fine-tuning. Experimental results demonstrate that the distribution-shifting property of diffusion model aligns well with our fine-tuned VLMs, significantly mitigating adversarial perturbations across varying intensities. The dataset and code are available at https://github.com/JarvisUSTC/DiffPure-RobustVLM.

cs.CV↗

arXiv2025

Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey

Ultra-high-definition (UHD) image restoration aims to specifically solve the problem of quality degradation in ultra-high-resolution images. Recent advancements in this field are predominantly driven by deep learning-based innovations, including enhancements in dataset construction, network architecture, sampling strategies, prior knowledge integration, and loss functions. In this paper, we systematically review recent progress in UHD image restoration, covering various aspects ranging from dataset construction to algorithm design. This serves as a valuable resource for understanding state-of-the-art developments in the field. We begin by summarizing degradation models for various image restoration subproblems, such as super-resolution, low-light enhancement, deblurring, dehazing, deraining, and desnowing, and emphasizing the unique challenges of their application to UHD image restoration. We then highlight existing UHD benchmark datasets and organize the literature according to degradation types and dataset construction methods. Following this, we showcase major milestones in deep learning-driven UHD image restoration, reviewing the progression of restoration tasks, technological developments, and evaluations of existing methods. We further propose a classification framework based on network architectures and sampling strategies, helping to clearly organize existing methods. Finally, we share insights into the current research landscape and propose directions for further advancements. A related repository is available at https://github.com/wlydlut/UHD-Image-Restoration-Survey.

cs.CV↗

arXiv2025

See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization

3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality.

cs.CV↗

arXiv2025

Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution

As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous deep-learning-based methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature.

eess.IV↗

arXiv2024

HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping windows to cut costs and ignore the useful information that exists across channels. To address this issue, this paper introduces a novel model, the Hybrid Attention Aggregation Transformer (HAAT), designed to better leverage feature information. HAAT is constructed by integrating Swin-Dense-Residual-Connected Blocks (SDRCB) with Hybrid Grid Attention Blocks (HGAB). SDRCB expands the receptive field while maintaining a streamlined architecture, resulting in enhanced performance. HGAB incorporates channel attention, sparse attention, and window attention to improve nonlocal feature fusion and achieve more visually compelling results. Experimental evaluations demonstrate that HAAT surpasses state-of-the-art methods on benchmark datasets. Keywords: Image super-resolution, Computer vision, Attention mechanism, Transformer

eess.IV↗

arXiv2024

Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection

Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings.

cs.CV↗