Streaming free-viewpoint video (FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting (3DGS), recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering. However, the storage requirements of these methods can reach up to 10MB per frame, making stream FVV in real-time impossible. To address this problem, we propose a novel FVV representation, dubbed StreamSTGS, designed for real-time streaming. StreamSTGS represents a dynamic scene using canonical 3D Gaussians, temporal features, and a deformation field. For high compression efficiency, we encode canonical Gaussian attributes as 2D images and temporal features as a video. This design not only enables real-time streaming, but also inherently supports adaptive bitrate control based on network condition without any extra training. Moreover, we propose a sliding window scheme to aggregate adjacent temporal features to learn local motions, and then introduce a transformer-guided auxiliary training module to learn global motions. On diverse FVV benchmarks, StreamSTGS demonstrates competitive performance on all metrics compared to state-of-the-art methods. Notably, StreamSTGS increases the PSNR by an average of 1dB while reducing the average frame size to just 170KB.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new concepts sequentially. Existing approaches primarily focus on minimizing interference between concepts, often neglecting the potential for positive inter-concept interactions. In this work, we present Forget Less by Learning from Parents (FLLP), a novel framework that introduces a parent-child inter-concept learning mechanism in hyperbolic space to mitigate forgetting. By embedding concept representations within a Lorentzian manifold, naturally suited to modeling tree-like hierarchies, we define parent-child relationships in which previously learned concepts serve as guidance for adapting to new ones. Our method not only preserves prior knowledge but also supports continual integration of new concepts. We validate FLLP on three public datasets and one synthetic benchmark, showing consistent improvements in both robustness and generalization.
Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While Direct Preference Optimization (DPO) has established a foundation for preference learning in large language models (LLMs), its extension to diffusion models remains limited in alignment performance. In this work, we propose an enhanced version of Diffusion-DPO by introducing a stable reference model update strategy. This strategy facilitates the exploration of better alignment solutions while maintaining training stability. Moreover, we design a timestep-aware optimization strategy that further boosts performance by addressing preference learning imbalance across timesteps. Through the synergistic combination of our exploration and timestep-aware optimization, our method significantly improves the alignment performance of Diffusion-DPO on human preference evaluation benchmarks, achieving state-of-the-art results.
State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep compressed attack (TCA), a novel framework that significantly reduces attack latency. TCA introduces two components founded on key insights into SNN behavior. First, timestep-level backpropagation (TLBP) is based on our finding that global temporal information in backpropagation to generate perturbations is not critical for an attack’s success, enabling per-timestep evaluation for early stopping. Second, adversarial membrane potential reuse (A-MPR) is motivated by the observation that initial timesteps are inefficiently spent accumulating membrane potential, a warm-up phase that can be pre-calculated and reused. Our experiments on VGG-11 and ResNet-17 with the CIFAR-10/100 and CIFAR10-DVS datasets show that TCA significantly reduces the required attack latency by up to 56.6% and 57.1% compared to SOTA methods in white-box and black-box settings, respectively, while maintaining a comparable attack success rate.
This paper addresses low-light video super-resolution (LVSR), aiming to restore high-resolution videos from low-light, low-resolution (LR) inputs. Existing LVSR methods often struggle to recover fine details due to limited contrast and insufficient high-frequency information. To overcome these challenges, we present RetinexEVSR, the first event-driven LVSR framework that leverages high-contrast event signals and Retinex-inspired priors to enhance video quality under low-light scenarios. Unlike previous approaches that directly fuse degraded signals, RetinexEVSR introduces a novel bidirectional cross-modal fusion strategy to extract and integrate meaningful cues from noisy event data and degraded RGB frames. Specifically, an illumination-guided event enhancement module is designed to progressively refine event features using illumination maps derived from the Retinex model, thereby suppressing low-light artifacts while preserving high-contrast details. Furthermore, we propose an event-guided reflectance enhancement module that utilizes the enhanced event features to dynamically recover reflectance details via a multi-scale fusion mechanism. Experimental results show that our RetinexEVSR achieves state-of-the-art performance on three datasets. Notably, on the SDSD benchmark, our method can get up to 2.95 dB gain while reducing runtime by 65% compared to prior event-based methods.
PINGS-X: Physics-Informed Normalized Gaussian Splatting with Axes Alignment for Efficient Super-Resolution of 4D Flow MRI
PDF ↗4D flow magnetic resonance imaging (MRI) is a reliable, non-invasive approach for estimating blood flow velocities, vital for cardiovascular diagnostics. Unlike conventional MRI focused on anatomical structures, 4D flow MRI requires high spatiotemporal resolution for early detection of critical conditions such as stenosis or aneurysms. However, achieving such resolution typically results in prolonged scan times, creating a trade-off between acquisition speed and prediction accuracy. Recent studies have leveraged physics-informed neural networks (PINNs) for super-resolution of MRI data, but their practical applicability is limited as the prohibitively slow training process must be performed for each patient. To overcome this limitation, we propose PINGS-X, a novel framework modeling high-resolution flow velocities using axes-aligned spatiotemporal Gaussian representations. Inspired by the effectiveness of 3D Gaussian splatting (3DGS) in novel view synthesis, PINGS-X extends this concept through several non-trivial novel innovations: (i) normalized Gaussian splatting with a formal convergence guarantee, (ii) axes-aligned Gaussians that simplify training for high-dimensional data while preserving accuracy and the convergence guarantee, and (iii) a Gaussian merging procedure to prevent degenerate solutions and boost computational efficiency. Experimental results on computational fluid dynamics (CFD) and real 4D flow MRI datasets demonstrate that PINGS-X substantially reduces training time while achieving superior super-resolution accuracy.
Recent progress in artificial intelligence has encouraged numerous attempts to understand and decode human visual system from brain signals. These prior works typically align neural activity independently with semantic and perceptual features extracted from images using pre-trained vision models. However, they fail to account for two key challenges: (1) the modality gap arising from the natural difference in the information level of representation between brain signals and images, and (2) the fact that semantic and perceptual features are highly entangled within neural activity. To address these issues, we utilize hyperbolic space, which is well-suited for considering differences in the amount of information and has the geometric property that geodesics between two points naturally bend toward the origin, where the representational capacity is lower. Leveraging these properties, we propose a novel framework, Hyperbolic Feature Interpolation (HyFI), which interpolates between semantic and perceptual visual features along hyperbolic geodesics. This enables both the fusion and compression of perceptual and semantic information, effectively reflecting the limited expressiveness of brain signals and the entangled nature of these features. As a result, it facilitates better alignment between brain and visual features. We demonstrate that HyFI achieves state-of-the-art performance in zero-shot brain-to-image retrieval, outperforming prior methods with Top-1 accuracy improvements of up to +17.3% on THINGS-EEG and +9.1% on THINGS-MEG.
Adversarial examples in neural networks have been extensively studied in Euclidean settings, but recent advances in _hyperbolic networks_ call for a reevaluation of attack strategies in non-Euclidean geometries. Existing methods such as FGSM and PGD apply perturbations without regard to the underlying hyperbolic structure, potentially leading to inefficient or geometrically inconsistent attacks. In this work, we propose a novel adversarial attack that explicitly leverages the geometric properties of hyperbolic space. Specifically, we compute the gradient of the loss function in the tangent space of hyperbolic space, decompose it into a radial (depth) component and an angular (semantic) component, and apply perturbation derived solely from the angular direction. Our method generates adversarial examples by focusing perturbations in semantically sensitive directions encoded in angular movement within the hyperbolic geometry. Empirical results on image classification, cross-modal retrieval tasks and network architectures demonstrate that our attack achieves higher fooling rates than conventional adversarial attacks, while producing high-impact perturbations with deeper insights into vulnerabilities of hyperbolic embeddings. This work highlights the importance of geometry-aware adversarial strategies in curved representation spaces and provides a principled framework for attacking hierarchical embeddings.
False Positives Matter: Multidimensional Localization Evaluation and Training-Free Explainable Adversarial Patch Defense
PDF ↗Adversarial patch attacks pose a significant threat to visual systems. While current patch purification-based defense methods enhance core metrics of visual perception models, they overlook the critical issue of false positive patches, severely compromising image usability. This paper reveals the inadequacy of existing evaluations for adversarial patch defenses, and pioneers a multidimensional adversarial patch localization evaluation framework, which comprehensively quantifies false positives, recall capability, and overall localization accuracy, providing a novel perspective for comparative analysis within the field. Furthermore, building upon the observation that false positives stem from a lack of semantic understanding, we propose a Semantic-Aware Training-free Explainable Defense method (SATED). SATED achieves zero-shot patch localization, false detection correction, and decision explanation by constructing a patch reasoning chain, while simultaneously performing integrated text-guided patch inpainting. Extensive experiments across digital and physical scenarios, detection and segmentation tasks, and diverse adversarial patches, demonstrate that our method significantly reduces false positives and doubles the overall patch localization accuracy, boosting both the generalizability and explainability of the defense.
With the rapid development of generative models, such as generative adversarial networks and diffusion models, the task of face forgery detection has emerged, aiming to identify forged faces in real-world scenarios. A key challenge for current face forgery detection models is improving generalization to unknown forgeries. To address this, we propose ResProto-FD, a framework that constructs residual prototype sets to capture diverse forgery cues and discriminative differences from real faces. Our novel perspective collects prototypes from the most informative residual features generated during training, enabling better representation of various forgery traces and real-vs-fake distinctions. First, we introduce a Visual-Language Residual Learning (VLRL) module based on the CLIP model. This module constructs residual features between image and text embeddings to capture inconsistencies between visual features and associated textual semantics. In doing so, it guides the model to attend to subtle visual forgery clues and enhances the discriminative power of image representations. Furthermore, we design a Gradient-aware Residual Prototypes (GRP) mechanism— a dynamic collection strategy that selectively stores uncertain residual features based on gradient signals to build the prototype sets. This enhances the model’s ability to generalize to unknown forgery types. Extensive experiments across various datasets and forgery methods demonstrate that ResProto-FD significantly improves generalization performance and consistently outperforms state-of-the-art methods.
EVOKE: Efficient and High-Fidelity EEG-to-Video Reconstruction via Decoupling Implicit Neural Representation
PDF ↗Visual neural decoding is an important research topic at the intersection of cognitive neuroscience and machine learning. While recent progress has been made in EEG-based neural decoding, reconstructing dynamic visual content remains challenging. In the field of EEG decoding, current models either utilize pre-trained encoders for feature extraction or employ graph neural networks to represent the spatio-temporal information embedding, resulting in poor model representation and high complexity. We propose EVOKE -- an innovative framework for zero-shot decoding of high-fidelity videos from EEG signals. EVOKE employs Implicit Neural Representations to perform complete spatial modeling of EEG and continuously decouples information in the EEG-INR perceptual space. Additionally, we construct a Hierarchical-aware Attention Module (HAM) to decode EEG from three feature anchors: visual, semantic, motion, and progressively control task inference. The Motion Attention Flow (MAF) we developed overcomes the limitations of capturing motion features in dynamic stimuli, creating a more robust representation that enhances reconstruction consistency. Comprehensive experiments prove that SOTA performance of EVOKE (0.353 SSIM, 0.715 CLIP-pcc). We provide an effective method for converting brain activity into rich visual experiences and set a new benchmark for brain multimodal generation.
Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding
PDF ↗Self-supervised 3D point cloud understanding is crucial for scene understanding, where Masked Autoencoders (MAE) have achieved excellent performance in point cloud representation learning. However, existing MAE-style methods fail to consider spatial-semantic variations in masking strategies, and joint learning with multi-view images often overlooks view redundancy. To address these challenges, we propose an MAE framework enhanced with reliable multi-view 2D-3D Key-part alignment and Reinforced masking, named as KR-MAE. Our approach comprises three key innovations: Reinforced Masking (RM) strategically samples visible tokens based on semantic saliency to enhance reconstruction fidelity; Reliable Multi-View Selector (RVS) dynamically refines the most informative image subset by filtering occluded or low-texture views, mitigating detrimental redundancy; Reliable-view 2D-3D Key-part Aligned Transformer (KAT) establishes semantic-aligned correspondence between salient 3D point cloud parts and reliable multi-view 2D image patches, leveraging rich texture cues from 2D images to compensate for sparse geometry in point cloud. Extensive experiments on 3D classification and segmentation benchmarks demonstrate that KR-MAE achieves state-of-the-art performance, surpassing prior multi-modal methods.
Versatile 3D tasks (e.g., generation or editing) distilling Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations resulting from prior view bias, which produces conflicting appearances between different views of an object. This bias causes subject-words to preferentially activate prior view features during cross-attention (CA) computation, regardless of the target view condition. To overcome this limitation, we conduct a comprehensive mathematical analysis to reveal the root cause of the prior view bias in T2I models. Moreover, we find different UNet-Layers show different effects of prior view in CA. Therefore, we propose a novel framework, TD-Attn, which addresses multi-view inconsistency via two key components: (1) the 3D-Aware Attention Guidance Module 3D-AAG constructs a view-consistent 3D attention Gaussian for subject-words to enforce spatial consistency across attention-focused regions, thereby compensating for the limited spatial information in 2D individual view CA maps; (2) the Hierarchical Attention Modulation Module (HAM) utilizes a semantic guidance tree to direct the Semantic Response Profiler (SRP) in localizing and modulating CA layers that are highly responsive to view conditions, where the enhanced CA maps further support the construction of more consistent 3D attention Gaussians. Notably, HAM facilitates semantic-specific interventions, enabling controllable and precise 3D editing. Extensive experiments firmly establish that TD-Attn has the potential to serve as a transformative, universal plugin, significantly enhancing multi-view consistency across a wide range of 3D tasks.
FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
PDF ↗Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization. However, achieving fine-grained independent control over multiple subjects remains challenging due to difficulties in preserving subject fidelity and preventing cross-subject attribute leakage. We present FocusDPO, a framework that adaptively identifies focus regions based on dynamic semantic correspondence and supervision image complexity. During training, our method progressively adjusts these focal areas across noise timesteps, implementing a weighted strategy that rewards information-rich patches while penalizing regions with low prediction confidence. The framework dynamically adjusts focus allocation during the DPO process according to the semantic complexity of reference images and establishes robust correspondence mappings between generated and reference subjects. Extensive experiments demonstrate that our method substantially enhances the performance of existing pre-trained personalized generation models, achieving state-of-the-art results on both single-subject and multi-subject personalized image synthesis benchmarks. Our method effectively mitigates attribute leakage while preserving superior subject fidelity across diverse generation scenarios, advancing the frontier of controllable multi-subject image synthesis.
MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos
PDF ↗Reconstructing realistic 3D human avatars from monocular videos is a challenging task due to the limited geometric information and complex non-rigid motion involved. We present MonoCloth, a new method for reconstructing and animating clothed human avatars from monocular videos. To overcome the limitations of monocular input, we introduce a part-based decomposition strategy that separates the avatar into body, face, hands, and clothing. This design reflects the varying levels of reconstruction difficulty and deformation complexity across these components. Specifically, we focus on detailed geometry recovery for the face and hands. For clothing, we propose a dedicated cloth simulation module that captures garment deformation using temporal motion cues and geometric constraints. Experimental results demonstrate that MonoCloth improves both visual reconstruction quality and animation realism compared to existing methods. Furthermore, thanks to its part-based design, MonoCloth also supports additional tasks such as clothing transfer, underscoring its versatility and practical utility.
AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
PDF ↗Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension, resulting in a larger key-value (KV) cache compared to static image embedding. A naive optimization strategy is to selectively focus on and retain KV caches of audio or video based on task. However, in the experiment, we observed that the attention of AV-LLMs to various modalities in the high layers is not strictly dependent on the task. In higher layers, the attention of AV-LLMs shifts more towards the video modality. In addition, we also found that directly integrating temporal KV of audio and spatial-temporal KV of video may lead to information confusion and significant performance degradation of AV-LLMs. If audio and video are processed indiscriminately, it may also lead to excessive compression or reservation of a certain modality, thereby disrupting the alignment between modalities. To address these challenges, we propose AccKV, an Adaptive-Focusing and Cross-Calibration KV cache optimization framework designed specifically for efficient AV-LLMs inference. Our method is based on layer adaptive focusing technology, selectively focusing on key modalities according to the characteristics of different layers, and enhances the recognition of heavy hitter tokens through attention redistribution. In addition, we propose a Cross-Calibration technique that first integrates inefficient KV caches within the audio and video modalities, and then aligns low-priority modality with high-priority modality to selectively evict KV cache of low-priority modality. The experimental results show that AccKV can significantly improve the computational efficiency of AV-LLMs while maintaining accuracy.
We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textual cues through a crossmodal prompt encoding scheme, Anomagic leverages rich contextual information to steer an inpainting‐based generation pipeline. A subsequent contrastive refinement strategy enforces precise alignment between synthesized anomalies and their masks, thereby bolstering downstream anomaly detection accuracy. To facilitate training, we introduce AnomVerse, a collection of 12,987 anomaly–mask–caption triplets assembled from 13 publicly available datasets, where captions are automatically generated by multimodal large language models using structured visual prompts and template‐based textual hints. Extensive experiments demonstrate that Anomagic trained on AnomVerse can synthesize more realistic and varied anomalies than prior methods, yielding superior improvements in downstream anomaly detection. Furthermore, Anomagic can generate anomalies for any normal‐category image using user‐defined prompts, establishing a versatile foundation model for anomaly generation.
Circuit-Think: A Multimodal Reasoning Framework for Automated Circuit-to-Netlist Translation with Trajectory-Guided Reinforcement Learning
PDF ↗Vision Language Models (VLMs) have shown strong performance in multimodal understanding, offering promise for the circuit-to-netlist translation task. However, the diverse component symbols and complex connections in circuit images challenge VLMs in understanding physical layouts and reasoning for electrical connection logic. To address these, we propose Circuit-Think, the first multimodal reasoning framework for the automated circuit-to-netlist translation task, which employs a Trajectory-Guided Reinforcement Learning (TGRL) paradigm for structured logical reasoning on circuit images. Circuit-Think initializes reasoning capabilities through supervised fine-tuning (SFT) on image-netlist pairs, then optimizes reasoning trajectories and netlist generation decisions using TGRL. Firstly, TGRL introduces a step-by-step reasoning paradigm, which guides the model with stepwise reward functions to simulate the human cognitive trajectory of ``identifying ports, recognizing devices, and inferring connections''. Secondly, we customize a multi-level reward that maps reasoning and answers into graph structures and node sets, jointly optimizing logical consistency and netlist accuracy via graph similarity and set matching. Thirdly, TGRL contains a reflective learning mechanism for low-scoring samples, which corrects the reasoning trajectory through reference answers as hints, avoiding local optima caused by sparse reward signals or erroneous reasoning paths. Moreover, we construct a circuit image-netlist reasoning dataset with 3,100 samples, offering step-by-step annotations for converting circuit images to netlists. Extensive experiments demonstrate that Circuit-Think achieves SOTA netlist accuracy and significantly improves the accuracy of downstream tasks.
Satire, a form of artistic expression combining humor with implicit critique, holds significant social value by illuminating societal issues. Despite its cultural and societal significance, satire comprehension, particularly in purely visual forms, remains a challenging task for current vision-language models. This task requires not only detecting satire but also deciphering its nuanced meaning and identifying the implicated entities. Existing models often fail to effectively integrate local entity relationships with global context, leading to misinterpretation, comprehension biases, and hallucinations. To address these limitations, we propose SatireDecoder, a training-free framework designed to enhance satirical image comprehension. Our approach proposes a multi-agent system performing visual cascaded decoupling to decompose images into fine-grained local and global semantic representations. In addition, we introduce a chain-of-thought reasoning strategy guided by uncertainty analysis, which breaks down the complex satire comprehension process into sequential subtasks with minimized uncertainty. Our method significantly improves interpretive accuracy while reducing hallucinations. Experimental results validate that SatireDecoder outperforms existing baselines in comprehending visual satire, offering a promising direction for vision-language reasoning in nuanced, high-level semantic tasks.
DECON: Reconstruction of Clothed-Geometric Multiple Humans from a Single Image via Geometry-Guided Decoupling
PDF ↗3D multi-human reconstruction from single images holds significant potential for advancing AR/VR applications. While remarkable progress has been made in single-human reconstruction, existing methods face challenges when reconstructing multiple humans. These challenges include: (1) severe inter-occlusion that disrupts individual body structures, and (2) the absence of physically plausible relative positioning among subjects. We present DECON, a novel DEcouple-and-reCONstruct framework that systematically addresses these limitations through two technical innovations: (1) a decouple-and-reconstruct framework with multi-view synthesis. It separates individuals and reconstructs detailed 3D bodies from a single image. (2) a Perspective-Aware Position Optimization (PAPO) approach. It ensures realistic positioning by fixing overlaps and gaps between subjects. Extensive experiments demonstrate our method's capability to reconstruct fully separated, anatomically complete 3D humans with clothed-geometric details and plausible interactions. Quantitative evaluations show a 54% reduction in Chamfer Distance and 35% in Point-to-Surface Distance compared to state-of-the-art methods.