In 3D point cloud object tracking, the motion-centric methods have emerged as a promising avenue due to its superior performance in modeling inter-frame motion. However, existing two-stage motion-based approaches suffer from fundamental limitations: (1) error accumulation due to decoupled optimization caused by explicit foreground segmentation prior to motion estimation, and (2) computational bottlenecks from sequential processing. To address these challenges, we propose FocusTrack, a novel one-stage paradigms tracking framework that unifies motion-semantics co-modeling through two core innovations: Inter-frame Motion Modeling (IMM) and Focus-and-Suppress Attention. The IMM module employs a temp-oral-difference siamese encoder to capture global motion patterns between adjacent frames. The Focus-and-Suppress attention that enhance the foreground semantics via motion-salient feature gating and suppress the background noise based on the temporal-aware motion context from IMM without explicit segmentation. Based on above two designs, FocusTrack enables end-to-end training with compact one-stage pipeline. Extensive experiments on prominent 3D tracking benchmarks, such as KITTI, nuScenes, and Waymo, demonstrate that the FocusTrack achieves new SOTA performance while running at a high speed with 105 FPS.
论文检索
输入标题、作者或关键词，从 1,620 篇学术成果中精准定位
Novel view synthesis and 4D reconstruction techniques predominantly rely on RGB cameras, thereby inheriting inherent limitations such as the dependence on adequate lighting, susceptibility to motion blur, and a limited dynamic range. Event cameras, offering advantages of low power, high temporal resolution and high dynamic range, have brought a new perspective to addressing the scene reconstruction challenges in high-speed motion and low-light scenes. To this end, we propose E-4DGS, the first event-driven dynamic Gaussian Splatting approach, for novel view synthesis from multi-view event streams with fast-moving cameras. Specifically, we introduce an event-based initialization scheme to ensure stable training and propose event-adaptive slicing splatting for time-aware reconstruction. Additionally, we employ intensity importance pruning to eliminate floating artifacts and enhance 3D consistency, while incorporating an adaptive contrast threshold for more precise optimization. We design a synthetic multi-view camera setup with six moving event cameras surrounding the object in a 360-degree configuration and provide a benchmark multi-view event stream dataset that captures challenging motion scenarios. Our approach outperforms both event-only and event-RGB fusion baselines and paves the way for the exploration of multi-view event-based reconstruction as a novel approach for rapid scene capture.
Multi-view clustering (MVC) for remote sensing data has attracted increasing attention due to its ability to exploit complementary information from multiple modalities without requiring labels. Recent graph-based deep clustering methods have shown strong potential in modeling spatial structures inherent in remote sensing data. However, existing approaches often emphasize capturing rich node relations while overlooking the optimization of these relations, leading to noisy connections and weak inter-cluster discrimination. To address this issue, we propose a novel Multi-view Graph Clustering with dual Relation Optimization (MDRO) framework tailored for remote sensing data. Specifically, we first segment the remote sensing image into irregular superpixels to reduce computational complexity and use superpixels as graph nodes. Then, MDRO constructs high-order similarity matrices guided by clustering distribution matrices and performs dual relation optimization to suppress noise relations and strengthen similarity relations. Furthermore, an optimal transportation-based constraint is introduced to guide the formation of robust and balanced cluster assignments, mitigating over-smoothing and trivial solutions in graph learning. Comprehensive experiments on four benchmark remote sensing datasets demonstrate that MDRO consistently outperforms existing single-view and multi-view clustering methods, achieving superior accuracy and robustness.
Image enhancement is a classical and enduring challenge in computer vision, seeking to produce high-quality images from corrupted observations. Unlike existing methods that target specific tasks, this work focuses on endowing the model with generic inductive capabilities, enabling fast adaptation to previously unseen enhancement tasks. Specifically, we investigate the inter-task weaving from both structural and parametric perspectives. Structurally, we establish inter-task weaving under a Hadamard view by designing a unified architecture called Degradation Unraveling Network (DUNet) tailored for diverse enhancement tasks, which incorporates a progressive degradation unraveling mechanism for fine-grained enhancement. Parametrically, we reveal the task-agnostic nature of degradation estimation parameters and treat them as meta-representations. A Bilevel Purify Modeling (BPM) framework is then proposed to reinforce their latent unified representation, where only the degradation-related parameters are optimized as meta-representations. Based on this design, a task-aware adaptation solution is further introduced, only the remaining parameters are allowed to be fine-tuned efficiently and enabling fast task adaptation. Extensive performance evaluations on three representative image enhancement tasks demonstrate the effectiveness and superiority of our method. The adaptability of our method is further verified by a series of algorithm analyses.
Digital images, serving as the primary carrier of information, have been wildly spread on the Internet. Image steganography is a technology that employs images as the carrier for information hiding. While current deep image steganography demonstrated impressive encoding abilities across various media, two serious problems have been overlooked in deep image-to-image steganography and hinder its application under real-world scenarios, which we define as the problem of Pixel Value Overflow and Gap of Precision. In this paper, we explore the cause of those problems and introduce a plug-and-play Universal Suppressor to solve the application problems of deep image-to-image steganography in real-world scenarios, which can be flexibly applied to various models with different structures. Experiments demonstrate that our Universal Suppressor performs well in existing state-of-the-art (SOTA) models and confers them with intrinsic robustness for real-world deployment. The code will be released at https://github.com/aoli-gei/USP.
Multimodal Industrial Anomaly Detection (MIAD)-fusing 3D point clouds and 2D RGB for product defect detection-is critical to quality inspection. However, existing MIAD methods assume all modalities are available and paired, overlooking real-scenario modality-missing and risking overfitting to incomplete data. To address these, we conduct the first comprehensive study on Modality-Incomplete Industrial Anomaly Detection (MIIAD) and establish MIIAD Bench , a benchmark covering diverse missing settings. Meanwhile, we propose RADAR, a robust two-stage Robust modAlity-instructive fusing & Detecting frAmewoRk. RADAR integrates i) a Modality-Incomplete Instruction mechanism-guiding the multimodal Transformer to focus more on available modal info, and ii) a Double-Pseudo Hybrid Module to highlight unique modality combinations and reduce overfitting. Our results show RADAR outperforms prior methods markedly on MIIAD Bench.
Remote photoplethysmography (rPPG) aims to extract non-contact physiological signals from facial videos and has shown great potential. However, existing rPPG approaches struggle to bridge the gap between source and target domains. Recent test-time adaptation (TTA) solutions typically optimize rPPG model for the incoming test videos using self-training loss under an unrealistic assumption that the target domain remains stationary. However, time-varying factors like weather and lighting in dynamic environments often cause continual domain shifts. The erroneous gradients accumulation from these shifts may corrupt the model's key parameters for physiological information, leading to catastrophic forgetting. Therefore, We propose a physiology-related parameters freezing strategy to retain such knowledge. It isolates physiology-related and domain-related parameters by assessing the model's uncertainty to current domain and freezes the physiology-related parameters during adaptation to prevent catastrophic forgetting. Moreover, the dynamic domain shifts with various non-physiological characteristics may lead to conflicting optimization objectives during TTA, which is manifested as the over-adapted model losing its adaptability to future domains. To fix over-adaptation, we propose a preemptive gradient modification strategy. It preemptively adapts to future domains and uses the acquired gradients to modify current adaptation, thereby preserving the model's adaptability. In summary, we propose a stable continual test-time adaptation (CTTA) framework for rPPG measurement, called PhysRAP, which Remembers the past, Adapts to the present, and Preempts the future. Extensive experiments show its state-of-the-art performance, especially in domain shifts. The code is available at https://github.com/xjtucsy/PhysRAP.
Most GCN-based methods model interacting individuals as independent graphs, neglecting their inherent inter-dependencies. Although recent approaches utilize predefined interaction adjacency matrices to integrate participants, these matrices fail to adaptively capture the dynamic and context-specific joint interactions across different actions. In this paper, we propose the Active Node Selection with External Attention Network (ASEA), an innovative approach that dynamically captures interaction relationships without predefined assumptions. Our method models each participant individually using a GCN to capture intra-personal relationships, facilitating a detailed representation of their actions. To identify the most relevant nodes for interaction modeling, we introduce the Adaptive Temporal Node Amplitude Calculation (AT-NAC) module, which estimates global node activity by combining spatial motion magnitude with adaptive temporal weighting, thereby highlighting salient motion patterns while reducing irrelevant or redundant information. A learnable threshold, regularized to prevent extreme variations, is defined to selectively identify the most informative nodes for interaction modeling. To capture interactions, we design the External Attention (EA) module to operate on active nodes, effectively modeling the interaction dynamics and semantic relationships between individuals. Extensive evaluations show that our method captures interaction relationships more effectively and flexibly, achieving state-of-the-art performance.
3D Gaussian Splatting has emerged as a prominent technique for representing and rendering complex 3D scenes, offering high fidelity and speed but resulting in large file sizes. Existing compression methods can reduce 3D Gaussian data size but often require costly retraining or refinement, which is memory- and compute-intensive and lacks flexibility for varying compression needs. This challenge grows as large-scale scenes become more common, increasing the demand for efficient, low-overhead compression methods - especially for resource-constrained mobile and edge devices. We introduce FlexGaussian, a flexible, cost-effective, training-free compression method for 3D Gaussian Splatting that combines mixed-precision quantization with attribute-discriminative pruning. FlexGaussian requires no retraining or refinement and adapts easily to diverse compression targets. Evaluations demonstrate up to 96.4% compression with minimal rendering quality loss (<1 dB PSNR drop) and support for mobile deployment. FlexGaussian achieves high compression ratios within seconds, running 1.7-2.1× faster than state-of-the-art training-free methods and 10-100×faster than training-involved approaches. Project page: https://supercomputing-system-ai-lab.github.io/projects/flexgaussian.
A significant challenge in audio deepfake detection (ADD) is to improve model generalization against unseen vocoders and other unknown factors, as existing methods often overfit to specific vocoder patterns or synthetic-irrelevant factors. To overcome this challenge, by focusing on vocoder-agnostic features and synthetic traces for generalizable ADD, we propose a novel dual-level disentanglement with meta-learning (ALDEN ) framework. Specifically, we first introduce an adversarial-training-based disentanglement learning (ADL) module to explicitly learn vocoder-agnostic and vocoder-specific features, effectively disentangling audio signals in terms of low-level characteristics. To suppress synthetic-irrelevant information, such as semantics and speaker identities, we simultaneously employ a reconstruction-based disentanglement learning (RDL) module, which further disentangles both synthetic-relevant and synthetic-irrelevant features from vocoder-agnostic features at a high-level of semantics. Additionally, as low-level non-semantic features are more critical in ADD, a vocoder-agnostic meta-learning (VAML) module is proposed to simulate cross-vocoder scenarios so as to further boost generalization performance. Extensive experiments demonstrate that ALDEN outperforms state-of-the-art methods in cross-vocoder and in-the-wild scenarios. The code, model, and supplementary materials will be released on the project page: https://beyond0814.github.io/ALDEN/.
The explosive growth of multi-source multimedia data has significantly increased the demands for transmission and storage, placing substantial pressure on bandwidth and storage infrastructures. While Autoregressive Compression Models (ACMs) have markedly improved compression efficiency through probabilistic prediction, current approaches remain constrained by two critical limitations: suboptimal compression ratios due to insufficient fine-grained feature extraction during probability modeling, and real-time processing bottlenecks caused by high resource consumption and low compression speeds. To address these challenges, we propose Efficient Dual-path Parallel Compression (EDPC), a hierarchically optimized compression framework that synergistically enhances modeling capability and execution efficiency via coordinated dual-path operations. At the modeling level, we introduce the Information Flow Refinement (IFR) metric grounded in mutual information theory, and design a Multi-path Byte Refinement Block (MBRB) to strengthen cross-byte dependency modeling via heterogeneous feature propagation. At the system level, we develop a Latent Transformation Engine (LTE) for compact high-dimensional feature representation and a Decoupled Pipeline Compression Architecture (DPCA) to eliminate encoding-decoding latency through pipelined parallelization. Experimental results demonstrate that EDPC achieves comprehensive improvements over state-of-the-art methods, including a 2.7× faster compression speed, and a 3.2% higher compression ratio. These advancements establish EDPC as an efficient solution for real-time processing of large-scale multimedia data in bandwidth-constrained scenarios. Our code is available at https://github.com/Magie0/EDPC.
Quantizing deep models prior to deployment is a widely adopted technique to speed up inference for various real-time applications, such as autonomous driving. However, quantized models often suffer from severe performance degradation in dynamic environments with potential domain shifts and this degradation is significantly more pronounced compared with their full-precision counterparts, as shown by our theoretical and empirical illustrations. To address the domain shift problem, test-time adaptation (TTA) has emerged as an effective solution by enabling models to learn adaptively from test data. Unfortunately, existing TTA methods are often impractical for quantized models as they typically rely on gradient backpropagation-an operation that is unsupported on quantized models due to vanishing gradients, as well as memory and latency constraints. In this paper, we focus on TTA for quantized models to improve their robustness and generalization ability efficiently. We propose a continual zeroth-order adaptation (ZOA) framework that enables efficient model adaptation using only two forward passes, eliminating the computational burden of existing methods. Moreover, we propose a domain knowledge management scheme to store and reuse different domain knowledge with negligible memory consumption, reducing the interference of different domain knowledge and fostering the knowledge accumulation during long-term adaptation. Experimental results on three classical architectures, including quantized transformer-based and CNN-based models, demonstrate the superiority of our methods for quantized model adaptation. On the quantized W6A6 ViT-B model, our ZOA is able to achieve a 5.0% improvement over the state-of-the-art FOA on ImageNet-C dataset. The source code is available at https://github.com/DengZeshuai/ZOA.
Recent forward prediction-based learned video compression (LVC) methods have achieved impressive results, even surpassing VVC reference software VTM under the Low Delay B (LDB) configuration. In contrast, learned bidirectional video compression (BVC) remains underexplored and still lags behind its forward-only counterparts. This performance gap is mainly due to the limited ability to extract diverse and accurate contexts: most existing BVCs primarily exploit temporal motion while neglecting non-local correlations across frames. Moreover, they lack the adaptability to dynamically suppress harmful contexts arising from fast motion or occlusion. To tackle these challenges, we propose BiECVC, a BVC framework that incorporates diversified local and non-local context modeling along with adaptive context gating. For local context enhancement, BiECVC reuses high-quality features from lower layers and aligns them using decoded motion vectors without introducing extra motion overhead. To model non-local dependencies efficiently, we adopt a linear attention mechanism that balances performance and complexity. To further mitigate the impact of inaccurate context prediction, we introduce Bidirectional Context Gating, inspired by data-dependent decay in recent autoregressive language models, to dynamically filter contextual information based on conditional coding results. Extensive experiments demonstrate that BiECVC achieves state-of-the-art performance, reducing the bit-rate by 13.4% and 15.7% compared to VTM 13.2 under the Random Access (Intra Period 32) with intra periods of 32 and 64, respectively. To our knowledge, BiECVC is the first learned video codec to surpass VTM 13.2 RA across all standard test datasets.
Dense multi-label action detection in untrimmed long videos is a formidable task, with end-to-end training particularly challenging due to computational constraints, typically involving separate stages of off-the-shelf feature extraction and subsequent global modeling for action prediction.Existing methods fail to optimize all modules jointly for better performance. We introduce FreETAD, a Frequency-based End-to-end Temporal Action Detection approach, which shifts the focus from local actionness scores to frequency component estimation. Using the short-term Fourier Transform, FreETAD reconstructs the global action curve seamlessly. With a DETR-like decoder and frequency-encoded vectors for queries, it enhances multi-scale time-frequency interactions. FreETAD leverages end-to-end training effectively, boosting the mAP by 1.5% on Charades and 2.7% on MultiTHUMOS.
With the rapid advancement of mobile imaging, capturing screens using smartphones has become a prevalent practice in distance learning and conference recording. However, moiré artifacts, caused by frequency aliasing between display screens and camera sensors, are further amplified by the image signal processing pipeline, leading to severe visual degradation. Existing sRGB domain demoiréing methods struggle with irreversible information loss, while recent two-stage raw domain approaches suffer from information bottlenecks and inference inefficiency. To address these limitations, we propose a single-stage raw domain demoiréing framework, Dual-Stream Demoiréing Network (DSDNet), which leverages the synergy of raw and YCbCr images to remove moiré while preserving luminance and color fidelity. Specifically, to guide luminance correction and moiré removal, we design a raw-to-YCbCr mapping pipeline and introduce the Synergic Attention with Dynamic Modulation (SADM) module. This module enriches the raw-to-sRGB conversion with cross-domain contextual features. Furthermore, to better guide color fidelity, we develop a Luminance-Chrominance Adaptive Transformer (LCAT), which decouples luminance and chrominance representations. Extensive experiments demonstrate that DSDNet outperforms state-of-the-art methods in both visual quality and quantitative evaluation and achieves an inference speed 2.4x faster than the second-best method, highlighting its practical advantages. We provide an anonymous online demo at https://dsdnet.github.io/DSDNet/.
Reconstructing transparent surfaces is essential for tasks such as robotic manipulation in labs, yet it poses a significant challenge for 3D reconstruction techniques like 3D Gaussian Splatting (3DGS). These methods often encounter a transparency-depth dilemma, where the pursuit of photorealistic rendering through standard α-blending undermines geometric precision, resulting in considerable depth estimation errors for transparent materials. To address this issue, we introduce Transparent Surface Gaussian Splatting (TSGS), a new framework that separates geometry learning from appearance refinement. In the geometry learning stage, TSGS focuses on geometry by using specular-suppressed inputs to accurately represent surfaces. In the second stage, TSGS improves visual fidelity through anisotropic specular modeling, crucially maintaining the established opacity to ensure geometric accuracy. To enhance depth inference, TSGS employs a first-surface depth extraction method. This technique uses a sliding window over α-blending weights to pinpoint the most likely surface location and calculates a robust weighted average depth. To evaluate the transparent surface reconstruction task under realistic conditions, we collect a TransLab dataset that includes complex transparent laboratory glassware. Extensive experiments on TransLab show that TSGS achieves accurate geometric reconstruction and realistic rendering of transparent objects simultaneously within the efficient 3DGS framework. Specifically, TSGS significantly surpasses current leading methods, achieving a 37.3% reduction in chamfer distance and an 8.0% improvement in F1 score compared to the top baseline. Additionally, TSGS maintains high-quality novel view synthesis, evidenced by a 0.41dB gain in PSNR, demonstrating that TSGS overcomes the transparency-depth dilemma. The code and dataset are available at https://longxiang-ai.github.io/TSGS/.
Proactive Deepfake detection via robust watermarks has seen interest ever since passive Deepfake detectors encountered challenges in identifying high-quality synthetic images. However, while demonstrating reasonable detection performance, they lack localization functionality and explainability in detection results. Additionally, the unstable robustness of watermarks can significantly affect the detection performance. In this study, we propose novel fractal watermarks for proactive Deepfake detection and localization, namely FractalForensics. Benefiting from the characteristics of fractals, we devise a parameter-driven watermark generation pipeline that derives fractal-based watermarks and performs one-way encryption of the selected parameters. Subsequently, we propose a semi-fragile watermarking framework for watermark embedding and recovery, trained to be robust against benign image processing operations and fragile when facing Deepfake manipulations in a black-box setting. Moreover, we introduce an entry-to-patch strategy that implicitly embeds the watermark matrix entries into image patches at corresponding positions, achieving localization of Deepfake manipulations. Extensive experiments demonstrate satisfactory robustness and fragility of our approach against common image processing operations and Deepfake manipulations, outperforming state-of-the-art semi-fragile watermarking algorithms and passive detectors for Deepfake detection. Furthermore, by highlighting the areas manipulated, our method provides explainability for the proactive Deepfake detection results.
Augmented Reality (AR) enhances Human-Robot Interaction (HRI) by offering diverse interaction methods. However, existing systems often fail to resolve the conflict between a user's implicit preferences and physical ergonomics, leading to suboptimal experiences. We introduce InteractGuide, a novel framework that, for the first time, uses a Large Language Model (LLM) as a central reasoning engine to dynamically balance these competing factors. Our system translates physiological signals into a symbolic ''Preference Memory'' that the LLM reasons over, alongside real-time ergonomic and contextual data, to provide personalized interaction recommendations. A 29-participant study confirms our architecture improves efficiency and experience compared to single-factor approaches, showing the potential of LLMs as reasoning engines for complex AR-HRI. This work presents a validated end-to-end architecture for user-centric interaction adaptation, demonstrating the potential of LLMs as reasoning engines in complex AR-HRI systems.
Localizing text under low-light conditions has gained attention, with typical approaches relying on two stage cascading modules that combine low-light enhancement and text localization. However, these often require additional enhancement modules and cause inefficiency in joint optimization. In this work, we address the challenge by adopting a novel approach: tailoring the detector for low light conditions through knowledge distillation from normal light conditions, without relying on any enhancement module. First, we design a Graph Topological Aggregation (GTA) model that utilizes the message passing mechanism of graph neural networks to structurally represent text topology and facilitate structured feature expression in knowledge transfer. We then introduce two specially designed knowledge transfer constraints aimed at enhancing the learning of text's multi-scale features and topological knowledge. Finally,we propose a Stage-wise Bilevel Knowledge Transfer learning strategy that designates the low-light learning process as the upper-level task, while treating normal light learning as the lower-level task, effectively addressing the coupling issues and sequential dependencies prevalent during the distillation process. Extensive experiments underscore the approach's superiority.
Since a building's floorplans are easily accessible, consistent over time, and inherently robust to changes in visual appearance, self-localization within the floorplan has attracted researchers' interest. However, since floorplans are minimalist representations of a building's structure, modal and geometric differences between visual perceptions and floorplans pose challenges to this task. While existing methods cleverly utilize 2D geometric features and pose filters to achieve promising performance, they fail to address the localization errors caused by frequent visual changes and view occlusions due to variously shaped 3D objects. To tackle these issues, this paper views the 2D Floorplan Localization (FLoc) problem from a higher dimension by injecting 3D geometric priors into the visual FLoc algorithm. For the 3D geometric prior modeling, we first model geometrically aware view invariance using multi-view constraints, i.e., leveraging imaging geometric principles to provide matching constraints between multiple images that see the same points. Then, we further model the view-scene aligned geometric priors, enhancing the cross-modal geometry-color correspondences by associating the scene's surface reconstruction with the RGB frames of the sequence. Both 3D priors are modeled through self-supervised contrastive learning, thus no additional geometric or semantic annotations are required. These 3D priors summarized in extensive realistic scenes bridge the modal gap while improving localization success without increasing the computational burden on the FLoc algorithm. Sufficient comparative studies demonstrate that our method significantly outperforms state-of-the-art methods and substantially boosts the FLoc accuracy.