论文检索

Haoqin Hong, Ding Fan, Fubin Dou, Zhi-Li Zhou, Haoran Sun, Congcong Zhu, Jingrun Chen

Recently, 3D Gaussian Splatting (3DGS), an explicit scene representation technique, has shown significant promise for dynamic novel-view synthesis from monocular video input. However, purely data-driven 3DGS often struggles to capture the diverse physics-driven motion patterns in dynamic scenes. To fill this gap, we propose Physics‑Informed Deformable Gaussian Splatting (PIDG), which treats each Gaussian particle as a Lagrangian material point with time-varying constitutive parameters and is supervised by 2D optical flow via motion projection. Specifically, we adopt static-dynamic decoupled 4D decomposed hash encoding to reconstruct geometry and motion efficiently. Subsequently, we impose the Cauchy momentum residual as a physics constraint, enabling independent prediction of each particle’s velocity and constitutive stress via a time-evolving material field. Finally, we further supervise data fitting by matching Lagrangian particle flow to camera-compensated optical flow, which accelerates convergence and improves generalization. Experiments on a custom physics-driven dataset as well as on standard synthetic and real-world datasets demonstrate significant gains in physical consistency and monocular dynamic reconstruction quality.

Hai Nguyen Hong, Duong Bach, Nam Phan, Cuong V. Nguyen, Cuong Do

For artificial intelligence to be safely deployed in high-risk domains, it must reliably know its limits. Selective prediction, or learning with a reject option, addresses this by enabling a model to abstain from prediction on inputs it deems unreliable, deferring them to a human expert. While deep ensembles have emerged as a leading approach for uncertainty estimation, their potential is often squandered by rejection methods that rely on static thresholds applied to the mean prediction. In this paper, we propose to learn a dynamic rejection policy directly from the rich behavioral signals of the ensemble itself. Our framework, DEGRE (Dynamic Ensembles Gating for REjection), is a novel meta-learning approach that trains a lightweight gating network on the ensemble’s consensus confidence and its internal disagreement (variance)— to explicitly discriminate between correct and incorrect predictions. Through rigorous evaluation across twelve diverse medical imaging benchmarks (MRI, X-ray, CT), DEGRE significantly advances selective prediction, achieving an average risk-coverage (AURC) reduction of 68.2% compared to the standard ensemble baseline. By providing a more reliable method for a model to recognize its own limitations, this learned, adaptive rejection mechanism paves the way for safer and more responsible integration of AI into critical clinical workflows.

Shinnosuke Hirano, Yuiga Wada, Kazuki Matsuda, Seitaro Otsuki, Komei Sugiura

We focus on the automatic evaluation of image captions in both reference-based and reference-free settings. Existing metrics based on large language models (LLMs) favor their own generations; therefore, the neutrality is in question. Most LLM-free metrics do not suffer from such an issue, whereas they do not always demonstrate high performance. To address these issues, we propose Pearl, an LLM-free supervised metric for image captioning, which is applicable to both reference-based and reference-free settings. We introduce a novel mechanism that learns the representations of image--caption and caption--caption similarities. Furthermore, we construct a human-annotated dataset for image captioning metrics that comprises approximately 333k human judgments collected from 2,360 annotators across over 75k images. Pearl outperformed other existing LLM-free metrics on the Composite, Flickr8K-Expert, Flickr8K-CF, Nebula, and FOIL datasets in both reference-based and reference-free settings.

Yunhong He, Zhengqing Yuan, Weixiang Sun, Yiyang Li, Yixin Liu, Yanfang Ye, Lichao Sun

Scaling Vision Transformers (ViTs) has yielded remarkable advancements in diverse vision tasks, albeit at the cost of escalating computational, memory, and parameter demands. Existing efficiency techniques typically address only one dimension, computation, memory, or parameters, lacking a cohesive approach. In this paper, we introduce Vision-MoR, a novel ViT architecture that unifies parameter sharing, spatially adaptive computation, and memory-efficient design into a single framework. Vision-MoR employs a spatial-aware router with shifted-window attention to dynamically assign per-patch recursion depths, coupled with a recursive Transformer loop enabling token-wise early exiting. This facilitates content-adaptive processing and recursive parameter reuse while preserving spatial locality. On ImageNet-1K, Vision-MoR Small attains 74.6% Top-1 accuracy with 140M FLOPs and 5.7M parameters, outperforming EfficientViT-M2 (70.8%) and SHViT-S1 (72.8%) at superior throughput. The Vision-MoR X-Large variant achieves 80.4% Top-1 and 95.2% Top-5 accuracy using 14.3M parameters and 2044M FLOPs, surpassing ResNet-50 and EfficientNet-B1. On COCO object detection, Vision-MoR X-Large yields 39.1 AP with the lowest latency among comparable models. These results underscore Vision-MoR's state-of-the-art accuracy-efficiency trade-offs, positioning it as a scalable, deployment-friendly backbone for real-time vision applications.

Yulin He, Wei Chen, Xinbiao Gan, Siqi Wang, Haotian Wang, Yusong Tan

Perceiving threats is an innate human instinct. During driving, humans naturally focus their attention on objects that pose real potential risks. Motivated by this observation, we shift the focus from traditional class-based detection to a novel task termed threat-oriented reasoning detection in autonomous driving. This task aims to localize threat objects and reason about their threat levels from a driver-centric perspective. To support this task, we build a benchmark comprising diverse corner-case scenarios, annotated by multiple experienced drivers to reflect human-aligned threat cognition. Given the reasoning demands of this task, we then explore the capabilities of multi-modal large language models (MLLMs) and introduce two methods based on whether the MLLM supports object detection: 1) For MLLMs lacking detection capability, we introduce ThreatCoT, a plug-and-play training-free method that combines chain-of-thought (CoT) with a visual expert toolchain to support step-by-step reasoning. 2) For MLLMs with detection support, we introduce ThreatReasoner, an end-to-end reinforcement learning (RL)-based method built on the GRPO algorithm, which enables per-object reasoning through a fully unsupervised reward strategy. Both quantitative and qualitative experiments show that our methods can effectively unlock the new capabilities of MLLM in threat-oriented reasoning detection.

Xiao He, Zhijun Tu, Kun Cheng, Mingrui Zhu, Jie Hu, Nannan Wang, Xinbo Gao

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models through Low-Rank Adaptation (LoRA) module to reconstruct high-resolution (HR) images. However, these dense Real-ISR models are limited in their ability to adaptively capture the heterogeneous characteristics of complex real-world degraded samples or enable knowledge sharing between inputs under equivalent computational budgets. To address this, we investigate the integration of sparse MoE into Real-ISR and propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution. We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert. This design enables flexible knowledge recombination while isolating fixed-position ranks as shared experts to preserve common-sense features and minimize routing redundancy. Furthermore, we develop a degradation estimation module leveraging CLIP embeddings and predefined positive-negative text pairs to compute relative degradation scores, dynamically guiding expert activation. To better accommodate varying sample complexities, we incorporate zero-expert slots and propose a degradation-aware load-balancing loss, which dynamically adjusts the number of active experts based on degradation severity, ensuring optimal computational resource allocation. Comprehensive experiments validate our framework's effectiveness and state-of-the-art performance.

Wenzhe He, Xiaojun Chen, Ruiqi Wang, Ruihui Li, Huilong Pi, Jiapeng Zhang, Zhuo Tang, Kenli Li

3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high‑fidelity reconstruction. However, their multi-step iterative sampling incurs significant computational overhead, limiting its real-time applicability. To address this, we propose LiNeXt: a lightweight, non‐diffusion network optimized for rapid and accurate point cloud completion. Specifically, LiNeXt first applies the Noise‑to‑Coarse (N2C) Module to denoise the input noisy point cloud in a single pass, thereby obviating the multi‑step iterative sampling of diffusion‑based methods. The Refine Module then takes the coarse point cloud and its intermediate features from the N2C Module to perform more precise refinement, further enhancing structural completeness. Furthermore, we observe that LiDAR point clouds exhibit a distance-dependent spatial distribution, being densely sampled at proximal ranges and sparsely sampled at distal ranges. Accordingly, we propose the Distance‑aware Selected Repeat strategy to generate a more uniformly distributed noisy point cloud. On the SemanticKITTI dataset, LiNeXt achieves a 199.8 times speedup in inference, reduces Chamfer Distance by 50.7 percent, and uses only 6.1 percent of the parameters compared with LiDiff. These results demonstrate the superior efficiency and effectiveness of LiNeXt for real-time scene completion.

Ping He, Rong Xiao, Wanying Xu, Chenwei Tang, Shudong Huang, Huajin Tang

Dynamic Vision Sensor (DVS) asynchronously records sparse events triggered by changes in pixel intensity, offering high temporal resolution and low latency. Existing frame-based methods process event data densely, violating its inherent sparsity and introducing computational redundancy. While asynchronous models preserve the event stream's native format, they often neglect spatial information, compromising their adaptability and efficiency. To address these limitations, we propose a Spatiotemporally Separated Sparse Network (S3Net) for efficient event stream encoding and learning. Specifically, we employ a learnable sparse encoding scheme to construct a voxel-structured representation that effectively extracts spatiotemporal relationships among event data. After that, we propose a dual-branch architecture to capture localized spatial dependencies and dynamic temporal patterns of event data. By explicitly decoupling spatial and temporal modeling, S3Net enables end-to-end asynchronous processing of variable-length event sequences, achieving both strong representational capacity and high computational efficiency. Experimental results on six event-based datasets demonstrate that S3Net achieves state-of-the-art performance. Compared to frame-based methods, it significantly reduces computational overhead and model complexity, while also outperforming existing asynchronous approaches in inference speed without compromising accuracy. Extensive experiments across six event-based datasets show that S3Net establishes new state-of-the-art performance. Our method reduces computational costs by 35% and model parameters by 27% compared to frame-based approaches, while delivering 1.58× faster inference than existing point-based methods at comparable accuracy levels.

Lian He, Meng Liu, Qilang Ye, Yu Zhou, Xiang Deng, Gangyi Ding

Understanding 3D scene-level affordances from natural language instructions is essential for enabling embodied agents to interact meaningfully in complex environments. However, this task remains challenging due to the need for semantic reasoning and spatial grounding. Existing methods mainly focus on object-level affordances or merely lift 2D predictions to 3D, neglecting rich geometric structure information in point clouds and incurring high computational costs. To address these limitations, we introduce Task-Aware 3D Scene-level Affordance segmentation (TASA), a novel geometry-optimized framework that jointly leverages 2D semantic cues and 3D geometric reasoning in a coarse-to-fine manner. To improve the affordance detection efficiency, TASA features a task-aware 2D affordance detection module to identify manipulable points from language and visual inputs, guiding the selection of task-relevant views. To fully exploit 3D geometric information, a 3D affordance refinement module is proposed to integrate 2D semantic priors with local 3D geometry, resulting in accurate and spatially coherent 3D affordance masks. Experiments on SceneFun3D demonstrate that TASA significantly outperforms the baselines in both accuracy and efficiency in scene-level affordance segmentation.

Haoran He, Yang Zhang, Liang Lin, Zhongwen Xu, Ling Pan

Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images), limiting their ability to model interactive and dynamic scenarios. In this paper, we propose Dynamic World Simulation (DWS), a novel approach to transform pre-trained video generative models into controllable world simulators capable of executing specified action trajectories. To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module that seamlessly integrates into any existing model. Instead of focusing on complex visual details, we demonstrate that consistent dynamic transition modeling is the key to building powerful world simulators. Building upon this insight, we further introduce a motion-reinforced loss that enhances action controllability by compelling the model to capture dynamic changes more effectively. Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models, achieving significant improvements in generating action-controllable, dynamically consistent videos across games and robotics domains. Moreover, to facilitate the applications of the learned world simulator in downstream tasks such as model-based reinforcement learning, we propose prioritized imagination to improve sample efficiency, demonstrating competitive performance compared with state-of-the-art methods.

Adam Hazimeh, Ke Wang, Mark Collier, Gilles Baechler, Efi Kokiopoulou, Pascal Frossard

Multimedia documents such as slide presentations and posters are designed to be interactive and easy to modify. Yet, they are often distributed in a static raster format, which limits editing and customization. Restoring their editability requires converting these raster images back into structured vector formats. However, existing geometric raster vectorization methods, which rely on low-level primitives like curves and polygons, fall short at this task. Specifically, when applied to complex documents like slides, they fail to preserve the high-level structure, resulting in a flat collection of shapes where the semantic distinction between image and text elements is lost. To overcome this limitation, we address the problem of semantic document derendering by introducing SliDer, a novel framework that uses Vision-Language Models (VLMs) to derender slide images as compact and editable Scalable Vector Graphic (SVG) representations. SliDer detects and extracts the attributes from individual image and text elements in a raster input and organizes them into a coherent SVG format. Crucially, the model iteratively refines its predictions during inference in a process analogous to human design, generating SVG code that more faithfully reconstructs the original raster upon rendering. Furthermore, we introduce Slide2SVG, a novel dataset comprising raster-SVG pairs of slide documents curated from real-world scientific presentations, to facilitate future research in this domain. Our results demonstrate that SliDer achieves a reconstruction LPIPS of 0.069, and is favored by human evaluators in 82.9% of cases compared to the strongest zero-shot VLM baseline.

Ruiyang Hao, Bowen Jing, Haibao Yu, Zaiqing Nie

Personalization, while extensively studied in conventional autonomous driving pipelines, has been largely overlooked in the context of end-to-end autonomous driving (E2EAD), despite its critical role in fostering user trust, safety perception, and real-world adoption. A primary bottleneck is the absence of large-scale real-world datasets that systematically capture driving preferences, severely limiting the development and evaluation of personalized E2EAD models. In this work, we introduce the first large-scale real-world dataset explicitly curated for personalized E2EAD, integrating comprehensive scene topology with rich dynamic context derived from agent dynamics and semantics inferred via a fine-tuned vision-language model (VLM). We propose a hybrid annotation pipeline that combines behavioral analysis, rule-and-distribution-based heuristics, and subjective semantic modeling guided by VLM reasoning, with final refinement through human-in-the-loop verification. Building upon this dataset, we introduce the first standardized benchmark for systematically evaluating personalized E2EAD models. Empirical evaluations on state-of-the-art architectures demonstrate that incorporating personalized driving preferences significantly improves behavioral alignment with human demonstrations.

Chen Hang, Haoming Chen, Xuwei Fang, Weisheng Xie, Xiangxiang Gao, Faming Fang, Guixu Zhang, Haichuan Song

In this paper, we investigate the limitations of the Vector Quantized Latent Diffusion Model (VQ-LDM) in restoration tasks. We identify a performance gap between the Vector Quantization (VQ) and Diffusion Model components, manifested as a significant discrepancy between the reconstruction quality of ground truth images processed via VQ autoregression and degraded images restored by VQ-LDM. Through experiments, we attribute this gap primarily to the lack of robustness in the mapped points of VQ within the original VQ-LDM framework. To address this issue, we propose a geometric based optimization approach. First, we introduce a simple yet effective method, termed interpolation-based latent initial state optimization, which mitigates the performance gap by replacing the original mapped points with interpolated values, supported by theoretical analysis. Here, the latent initial state refers specifically to the input of the diffusion model. Building upon this, we further propose a Chebyshev center-based latent initial state optimization, an elegant theoretical solution from a geometric perspective, that further enhances restoration performance. Our improvements consistently achieve superior results across nine benchmark datasets.

Zheng Han, Xiaobin Zhu, Chun Yang, Jingyan Qin, Xu-Cheng Yin

In few-shot learning, utilizing local and global geometric priors to capture both subtle local class metrics and coarse global structures within the meta-task are important to obtain discriminative embeddings. However, existing graph-based and curvature-based few-shot approaches only focus on either one kind of geometric prior but neglect the other. To effectively utilize the pros of these two paradigms, we propose a novel Dual-Geometry Graph Network (DGGN) to adaptively integrate the local and global geometric priors via two key pathways. Specifically, the local-wise metric modeling pathway utilizes Ollivier-Ricci curvature to capture task-specific local class metrics among the instances, and the global-wise connectivity modeling pathway utilizes resistive embedding to capture global instance distributions and connectivity patterns of the entire meta-task. In addition, we introduce two new regularization loss functions to explicitly enhance the geometric representation ability of the local and global pathways respectively. We validate that DGGN's superior performance stems from its adaptively topological refinements by measuring the graph edit distance, demonstrating its ability to match the underlying data distribution. Extensive experiments show that DGGN sets a new state-of-the-art on standard, cross-domain, and semi-supervised few-shot benchmarks.

Yuhang Han, Xuyang Liu, Zihan Zhang, Pengxiang Ding, Junjie Chen, Honggang Chen, Donglin Wang, Qingsen Yan, Siteng Huang

The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-world deployment. In the paper, we devise a ''filter-correlate-compress'' framework to accelerate the MLLM by systematically optimizing multimodal context length during prefilling. The framework first implements FiCoCo-V, a training-free method operating within the vision encoder. It employs a redundancy-based token discard mechanism that uses a novel integrated metric to accurately filter out redundant visual tokens. To mitigate information loss, the framework introduces a correlation-based information recycling mechanism that allows preserved tokens to selectively recycle information from correlated discarded tokens with a self-preserving compression, thereby preventing the dilution of their own core content. The framework's FiCoCo-L variant further leverages task-aware textual priors to perform token reduction directly within the LLM decoder. Extensive experiments demonstrate that the FiCoCo series effectively accelerates a range of MLLMs, achieves up to 14.7× FLOPs reduction with 93.6% performance retention. Our methods consistently outperform state-of-the-art training-free approaches, showcasing effectiveness and generalizability across model architectures, sizes, and tasks without requiring retraining.

Shuo Han, Qibing Qin, Kezhen Xie, Wenfeng Zhang, Lei Huang

Hashing techniques are widely adopted in large-scale cross-modal retrieval due to their efficiency and low storage cost. However, semantic ambiguities, including polysemy, multi-object images, and missing semantic descriptions, significantly degrade the accuracy of alignment and retrieval performance. Most existing methods rely on one-to-one mappings that preserve only global average semantics, which fail to capture the intrinsic polysemous structures embedded within individual samples. To address this issue, we propose a novel Deep Polysemic Semantic Instance Hashing (DPSIH) method and design a Diverse Semantic Instance Embedding (DSIE) module. This module integrates local and global features through multi-head self-attention and residual learning, generating multiple diverse embeddings per sample to effectively capture fine-grained and polysemous semantic structures. Furthermore, we design a multi-embedding semantic correlation constraint that relaxes strict alignment restrictions to improve robustness under partial alignment, and introduce Maximum Mean Discrepancy (MMD) regularization to alleviate cross-modal distribution shifts. Additionally, an embedding diversity mechanism is proposed to prevent all embeddings from collapsing into a central or averaged representation, thereby enhancing semantic diversity. Extensive experiments on four benchmark datasets demonstrate that DPSIH significantly outperforms state-of-the-art methods and effectively improves the modeling of semantic ambiguity in cross-modal retrieval tasks.

Shuhao Han, Haotian Fan, Jiachen Fu, Liang Li, Tao Li, Junhui Cui, Yunqiu Wang, Yang Tai, Jingwei Sun, Chun-Le Guo 等

Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated methods emerge to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated methods is constrained by the limited scale of existing datasets. Additionally, existing datasets lack the capacity to assess the performance of automated methods at a fine-grained level. In this study, we contribute an EvalMuse-40K dataset, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our dataset. This allows us to comprehensively evaluate the performance of image-text alignment methods for T2I models. Based on this dataset, we introduce an efficient automated evaluation method termed FGA-BLIP2, which enables Fine-Grained Alignment evaluation solely by inputting images and text leveraging BLIP2, without visual question answering for each fine-grained element. Experimental results show the proposed FGA-BLIP2 efficiently achieves good performance on multiple image-text alignment datasets. Meanwhile, benefiting from the high efficiency and fine-grained evaluation capability of FGA-BLIP2, we apply it as a reward model to improve text-to-image models, which effectively enhances the image-text alignment ability of text-to-image models.

Shuaihao Han, Tingfa Xu, Peifu Liu, Jianan Li

Aerial object detection faces significant challenges in real-world scenarios, such as small objects and extensive background interference, which limit the performance of RGB-based detectors with insufficient discriminative information. Multispectral images (MSIs) capture additional spectral cues across multiple bands, offering a promising alternative. However, the lack of training data has been the primary bottleneck to exploiting the potential of MSIs. To address this gap, we introduce the first large-scale dataset for Multispectral Object Detection in Aerial images (MODA), which comprises 14,041 MSIs and 330,191 annotations across diverse, challenging scenarios, providing a comprehensive data foundation for this field. Furthermore, to overcome challenges inherent to aerial object detection using MSIs, we propose OSSDet, a framework that integrates spectral and spatial information with object-aware cues. OSSDet employs a cascaded spectral-spatial modulation structure to optimize target perception, aggregates spectrally related features by exploiting spectral similarities to reinforce intra-object correlations, and suppresses irrelevant background via object-aware masking. Moreover, cross-spectral attention further refines object-related representations under explicit object-aware guidance. Extensive experiments demonstrate that OSSDet outperforms existing methods with comparable parameters and efficiency.

Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He, Shaokun Wang, Qiang Wang, Yihong Gong

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in forgetting and inconsistent feature alignment. We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning. GOAL conducts supervised alignment for labeled samples and confidence-guided alignment for novel samples, enabling stable integration of new classes without disrupting old ones. Experiments on four benchmarks show that GOAL outperforms prior methods, reducing forgetting by 16.1% and boosting novel class discovery by 3.2%, establishing a strong solution for long-horizon continual discovery.

Haoliang Han, Ziyuan Luo, Jun Qi, Anderson Rocha, Renjie Wan

Recent advances in editing technologies for 3D Gaussian Splatting (3DGS) have made it simple to manipulate 3D scenes. However, these technologies raise concerns about potential malicious manipulation of 3D content. To avoid such malicious applications, localizing tampered regions becomes crucial. In this paper, we propose GS-Checker, a novel method for locating tampered areas in 3DGS models. Our approach integrates a 3D tampering attribute into the 3D Gaussian parameters to indicate whether the Gaussian has been tampered. Additionally, we design a 3D contrastive mechanism by comparing the similarity of key attributes between 3D Gaussians to seek tampering cues at 3D level. Furthermore, we introduce a cyclic optimization strategy to refine the 3D tampering attribute, enabling more accurate tampering localization. Notably, our approach does not require expensive 3D labels for supervision. Extensive experimental results demonstrate the effectiveness of our proposed method to locate the tampered 3DGS area.