论文检索

Yingjie Guo, Jinxin Lv, Wei Fang, Qiang Li, Zhiwei Wang

Locating vertebral landmarks on anteroposterior (AP) X-ray images is challenging due to the tissue overlap. Despite the great progress of heatmap-based methods, they often predict missing/false points, which are intolerable in the downstream applications like scoliosis assessment. In this paper, we instead modernize the classic point-regression scheme, and propose a novel model termed RouterNet to locate the 68 vertebral landmarks completely and accurately. RouterNet starts from an initial root point, and then gradually routes it onto more and more points with finer and finer semantics. RouterNet naturally couples such point routing process with its hierarchical and multi-scale feature learning. That is, lower-scale feature maps are utilized to regress points with coarser semantics, and the regressed points pilot a more focused local feature extraction on the next higher-scale map to route onto their subsequent positions with finer semantics. With this divide-and-conquer, RouterNet alleviates the task difficulty, and can robustly localize by routing from the whole spinal center to 17 vertebral centers, and further to their 68 corner points. Extensive and comprehensive experiments on both public and private datasets demonstrate our superior performance over other state-of-the-arts, by decreasing NMSE by 73.8% for landmark localization, and SMAPE by 14.8% for the downstream scoliosis assessment.

Yijia Guo, Wenkai Huang, Yang Li, Gaolei Li, Hang Zhang, Liwen Hu, Jianhua Li, Tiejun Huang, Lei Ma

3D Gaussian splatting (3DGS) has demonstrated impressive 3D reconstruction performance with explicit scene representations. Given the widespread application of 3DGS in 3D reconstruction and generation tasks, there is an urgent need to protect the copyright of 3DGS assets. However, existing copyright protection techniques for 3DGS overlook the usability of 3D assets, posing challenges for practical deployment. Here we describe splats in splats, the first 3DGS steganography framework that embeds 3D content in 3DGS itself without modifying any attributes. To achieve this, we take a deep insight into spherical harmonics (SH) and devise an importance-graded SH coefficient encryption strategy to embed the hidden SH coefficients. Furthermore, we employ a convolutional autoencoder to establish a mapping between the original Gaussian primitives' opacity and the hidden Gaussian primitives' opacity. Extensive experiments indicate that our method significantly outperforms existing 3D steganography techniques, with 5.31% higher scene fidelity and 3x faster rendering speed, while ensuring security, robustness, and user experience.

Yifu Guo, Yuquan Lu, Wentao Zhang, Zishan Xu, Dexia Chen, Siyu Zhang, Yizhe Zhang, Ruixuan Wang

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods typically employ single-stage encoder-decoder architectures where segmentation masks and class labels are tightly coupled, leading to interference between old and new class learning and suboptimal retention-plasticity balance. We introduce DecoupleCSS, a novel two-stage framework for CSS. By decoupling class-aware detection from class-agnostic segmentation, DecoupleCSS enables more effective continual learning, preserving past knowledge while learning new classes. The first stage leverages pre-trained text and image encoders, adapted using LoRA, to encode class-specific information and generate location-aware prompts. In the second stage, the Segment Anything Model (SAM) is employed to produce precise segmentation masks, ensuring that segmentation knowledge is shared across both new and previous classes. This approach improves the balance between retention and adaptability in CSS, achieving state-of-the-art performance across a variety of challenging tasks.

Xusheng Guo, Wanfa Zhang, Shijia Zhao, Qiming Xia, Xiaolong Xie, Mingming Wang, Hai Wu, Chenglu Wen

Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them through self-training iterations. However, these pseudo-labels are often incorrect at the beginning of training, resulting in misleading the optimization process. Moreover, effectively filtering and refining them remains a critical challenge. In this paper, we propose $\textbf{OWL}$ for unsupervised 3D object detection by occupancy guided warm-up and large-model priors reasoning. OWL first employs an Occupancy Guided Warm-up (OGW) strategy to initialize the backbone weight with spatial perception capabilities, mitigating the interference of incorrect pseudo-labels on network convergence. Furthermore, OWL introduces an Instance-Cued Reasoning (ICR) module that leverages the prior knowledge of large models to assess pseudo-label quality, enabling precise filtering and refinement. Finally, we design a WAS (Weight-adapted Self-training) strategy to dynamically re-weight pseudo-labels, improving the performance through self-training. Extensive experiments on Waymo Open Dataset (WOD) and KITTI demonstrate that OWL outperforms state-of-the-art unsupervised methods by over 15.0\% mAP, revealing the effectiveness of our method.

Xucheng Guo, Bing Li, Lin Wang, Yiran Shen

In this paper, we present Ev-iCRF, a novel self-supervised pipeline for high dynamic range (HDR) image reconstruction from a single-exposure low dynamic range (LDR) image, guided by asynchronous event streams generated by a bio-inspired event camera. The highlight of Ev-iCRF lies in its formulation of the inverse camera response function (iCRF) based on Event-LDR Correspondence. By leveraging the HDR properties of event data, the method enables direct iCRF estimation, offering a new perspective for event-guided HDR imaging. The pipeline is trained in a self-supervised manner using formulation-driven iCRF estimation loss and refinement loss, without the need for synchronized HDR supervision. Ev-iCRF adopts a two-stage coarse-to-fine reconstruction pipeline, allowing effective fusion of features from both LDR image and event data. The event information is used to optimize the iCRF, enabling accurate HDR reconstruction from LDR inputs. We evaluate Ev-iCRF on real-world datasets, and results show that it outperforms state-of-the-art methods in HDR reconstruction accuracy. Moreover, the reconstructed images demonstrate improved texture fidelity and structural detail.

Xiang Guo, Ruimin Hu, Dongliang Zhu, Mei Wang

Person re-identification (Re-ID) under extremely low-light conditions suffers from severe image degradation, which significantly impairs the extraction of identity-discriminative features. Existing methods struggle to recover semantic information that is obscured under poor illumination. To better understand this problem, we conduct a comprehensive analysis of the semantic modeling behavior of Re-ID models in low-light settings. For the first time, we investigate the norm distributions of Query (Q), Key (K), and Value (V) vectors within the attention module and observe that, as illumination decreases, the norm of Query vectors in pedestrian regions drops significantly. This leads to dispersed attention and degraded feature representations. To address this issue, we propose a novel framework named Norm-Ratio Attention and Semantic Recovery Distillation Network (NRSRD), which consists of two key components: a Norm-Ratio Attention Module (NRA) and a Semantic Recovery Distillation Module (SRD). The former dynamically adjusts attention responses based on the ratio of K/Q vector norms, enhancing structural region perception while suppressing background interference. The latter transfers discriminative semantic knowledge from high-illumination auxiliary data to the low-light model, compensating for the semantic degradation caused by poor lighting. Extensive experiments on multiple publicly available low-light Re-ID benchmarks demonstrate the effectiveness and superiority of the proposed method.

Shaojie Guo, Yingying Fang, Junkang Zhang, Yan Wang

Deep unrolling models (DUMs) have shown great poten-tial in sparse-view CT reconstruction by combining itera-tive optimization and deep learning. However, most DUMsinsufficiently account for physical degradation from sparse-view imaging, leading to slow convergence and persistentartifacts. To address this, we propose PAUM, a Physics-Aware Accelerated Unrolling Model explicitly incorporatingCT imaging physics into the iterative reconstruction. PAUMfirst introduces a Dual-Domain Physics-Aware Extrapolation(DDPE) module. By modeling dual-domain degradations, itperforms row-wise extrapolation in the sinogram domain toimprove missing view recovery, and pixel-wise extrapolationin the image domain to address spatially variant degradationfrom incomplete backprojection. This physics-aware extrap-olation aligns optimization dynamics with underlying physi-cal imaging degradation, significantly enhances structural up-dates, thereby accelerating convergence. Subsequently, wedevelop a lightweight Block-Attention Deformable Regu-larization Network (BDRN), leveraging deformable convo-lutions and block-wise attention to model spatially variantand structured artifact physical characteristics. This enablesspatially adaptive regularization on extrapolated results, ef-fectively improving reconstruction quality. Extensive exper-iments demonstrate PAUM achieves over 1dB improvementcompared to SOTA methods, while reducing iteration countby 50%.

Qingju Guo, Shuang Li, Binhui Xie, Jing Geng, Wei Li

3D semantic occupancy prediction offers a nuanced representation of the surrounding environment, which is crucial for ensuring the safety of autonomous driving. However, fine-grained scene representations inevitably result in cubic growth in data scale, which imposes substantial demands on model architecture and computational complexity, especially in high-resolution scenarios. Existing approaches for handling high-resolution scenes typically obtain fine-grained features by grid sampling on low-resolution feature map, resulting in limited sparsity and insufficient feature interaction. This paper presents a framework leveraging SParse representation and SCalable feature interaction to address the aforementioned challenges, called SPSC. Specifically, we maintain sparsity by progressively pruning unoccupied queries during the coarse-to-fine process, thereby reducing the scale of data that the model needs to handle. Subsequently, we introduce query serialization, which transforms queries into an ordered sequence while preserving their spatial structure, This enables fine-grained feature interaction while maintaining linear computational complexity and a larger receptive field. Without complex architectural designs, SPSC significantly outperforms SOTA approaches, relatively enhances the mIoU by 12.0%, 11.0% and 4.8% on nuScenes-Occupancy dataset under the muli-modal, LiDAR and camera settings, respectively.

Qianren Guo, Yuehang Wang, Yongji Zhang, Qi Chu, Sen Liu, Yu Jiang

Effectively capturing co-occurrence signals, such as hand shapes, facial expressions, and body postures, is critical for semantic understanding in sign language recognition (SLR) and translation (SLT). Although skeleton data offer greater efficiency and robustness than RGB inputs, existing methods typically rely on pairwise graph structures, limiting their ability to model complex high-order interactions across body regions. To address this limitation, we propose HyperSign, a hierarchical hypergraph neural network that systematically captures high-order co-occurrence patterns among diverse body parts. The Co-occurrence Graph Perception Module jointly learns relational structures via three complementary pathways: (1) traditional graph convolutions for modeling physical joint connections, (2) dynamic geometric hypergraphs constructed via k-nearest neighbors to encode local spatial patterns, and (3) soft hypergraphs generated by learnable prototypes to reveal latent semantic associations. To further enhance structural modeling and semantic consistency, a Meta-Part Hypergraph Fusion Module abstracts feature streams from the hands, face, and body into unified hypergraph nodes, while leveraging empirically derived co-occurrence priors to model high-order cross-part dependencies. Moreover, an uncertainty-aware collaborative distillation mechanism guides the model to focus on critical body regions. Extensive experiments on standard SLR and SLT benchmarks (e.g., PHOENIX-2014, PHOENIX-2014T, and CSL-Daily) demonstrate that HyperSign not only outperforms existing skeleton-based approaches in both speed and accuracy but also achieves competitive or superior results compared to several state-of-the-art RGB-based methods across multiple evaluation metrics.

Qi Guo, Xiaojun Jia, Shanmin Pang, Simeng Qin, Lin Wang, Ju Jia, Yang Liu, Qing Guo

Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vulnerable to adversarial attacks—particularly adversarial patch attacks—which can pose serious threats in real-world scenarios. Existing patch-based attack methods are primarily designed for object detection models. Due to the more complex architectures and strong reasoning capabilities of MLLMs, these approaches perform poorly when transferred to MLLM-based systems. To address these limitations, we propose PhysPatch, a physically realizable and transferable adversarial patch framework tailored for MLLM-based AD systems. PhysPatch jointly optimizes patch location, shape, and content to enhance attack effectiveness and real-world applicability. It introduces a semantic-based mask initialization strategy for realistic placement, an SVD-based local alignment loss with patch-guided crop-resize to improve transferability, and a potential field-based mask refinement method. Extensive experiments across open-source, commercial, and reasoning-capable MLLMs demonstrate that PhysPatch significantly outperforms state-of-the-art (SOTA) methods in steering MLLM-based AD systems toward target-aligned perception and planning outputs. Moreover, PhysPatch consistently places adversarial patches in physically feasible regions of AD scenes, ensuring strong real-world applicability and deployability.

Jiaxun Guo, Manar Amayri, Nizar Bouguila, Xin Liu, Wentao Fan

Recent advances in rotation-invariant (RI) learning for 3D point clouds typically replace raw coordinates with handcrafted RI features to ensure robustness under arbitrary rotations. However, these approaches often suffer from the loss of global pose information, making them incapable of distinguishing geometrically similar but spatially distinct structures. We identify that this limitation stems from the restricted receptive field in existing RI methods, leading to Wing–tip feature collapse, a failure to differentiate symmetric components (e.g., left and right airplane wings) due to indistinguishable local geometries. To overcome this challenge, we introduce the Shadow-informed Pose Feature (SiPF), which augments local RI descriptors with a globally consistent reference point (referred to as the “shadow”) derived from a learned shared rotation. This mechanism enables the model to preserve global pose awareness while maintaining rotation invariance. We further propose Rotation-invariant Attention Convolution (RIAttnConv), an attention-based operator that integrates SiPFs into the feature aggregation process, thereby enhancing the model’s capacity to distinguish structurally similar components. Additionally, we design a task-adaptive shadow locating module based on the Bingham distribution over unit quaternions, which dynamically learns the optimal global rotation for constructing consistent shadows. Extensive experiments on 3D classification and part segmentation benchmarks demonstrate that our approach substantially outperforms existing RI methods, particularly in tasks requiring fine-grained spatial discrimination under arbitrary rotations.

Chuchen Guo, Zheng Liu, Ying He

Recovering precise surface geometry from corrupted point clouds remains a core challenge in 3D vision. Although existing denoising techniques achieve remarkable success, balancing noise removal with preserving intricate geometric details continues to pose difficulties. A critical limitation of current methods is that their adaptive feature aggregation mechanisms rely heavily on intermediate network features that have not been explicitly regularized, resulting in unstable guidance signals. This instability restricts the capability of the network to optimally differentiate true geometric details from noise. To overcome this limitation, we propose a novel deep learning framework that explicitly learns structured representations as robust priors to guide feature refinement. Our approach first derives a set of representative local structural primitives from input features by means of a learned codebook. This learned structured representation then serves as a robust conditional signal, directing a subsequent feature fusion mechanism to dynamically aggregate information in a structure-aware manner, thereby more effectively discerning noise and meticulously reconstructing geometric details. Extensive experiments on several benchmarks have demonstrated the superiority of our framework over existing advanced techniques in terms of detail preservation and noise suppression.

Bingyang Guo, Qiang Zuo, Ruiyun Yu

The effective segmentation of 3D data is crucial for a wide range of industrial applications, especially for detecting subtle defects in the field of integrated circuits (IC). Ceramic package substrates (CPS), as an important electronic material, are essential in IC packaging owing to their superior physical and chemical properties. However, the complex structure and minor defects of CPS, along with the absence of a publically available dataset, significantly hinder the development of CPS surface defect detection. In this study, we construct a high-quality point cloud dataset for 3D segmentation of surface defects in CPS, i.e., CPS3D-Seg, which has the best point resolution and precision compared to existing 3D industrial datasets. CPS3D-Seg consists of 1300 point cloud samples under 20 product categories, and each sample provides accurate point-level annotations. Meanwhile, we conduct a comprehensive benchmark based on SOTA point cloud segmentation algorithms to validate the effectiveness of CPS3D-Seg. Additionally, we propose a novel 3D segmentation method based on causal inference (CINet), which quantifies potential confounders in point clouds through Structural Refine (SR) and Quality Assessment (QA) Modules. Extensive experiments demonstrate that CINet significantly outperforms existing algorithms in both mIoU and accuracy.

Tianwei Guan, Haozhen Wei, Yuhan Zhou, Jun Ma, Zecheng Xu, Zhiying Jiang, Jinyuan Liu, Xingyuan Li

Infrared and Visible Image Fusion (IVIF) integrates complementary information from distinct modalities to enhance image quality. However, the effectiveness declines under unseen conditions such as novel weather or scenes, due to domain shifts primarily from variations of data distribution in the visible modality, while the infrared modality remains relatively stable. To overcome domain shifts caused by the imbalance between modalities during image fusion, we propose a Domain Adaptation Guided Infrared and Visible Image Fusion method, termed DAFusion, leveraging a dual-rank domain adapter to enable fast adaptation to diverse adverse conditions during image fusion. Specifically, trainable low-rank and high-rank embedding spaces are respectively used to capture knowledge common across domains (domain-shared) and those unique to target domains (domain-specific). To leverage the dual-rank adapter more effectively, we develop a homeostatic knowledge allotment strategy to integrate the distinct types of knowledge dynamically based on the uncertainty value of target domains. Since domain adaptation typically optimizes for feature alignment across domains and emphasizes invariance rather than preserving specific cues critical for image fusion, while the fusion objective requires retaining discriminative and complementary features, a conflict between the two modules appears. To reconcile this, we further adopt a bi-level optimization framework that structurally decouples the two objectives, enabling the fusion module to steer the adaptation process while benefiting in return from domain-aligned representations. Experimental results on three benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches, achieving both an enhancement in fusion quality and an improvement on subsequent high-level tasks.

Runwei Guan, Rongsheng Hu, Shangshu Chen, Ningyuan Xiao, Xue Xia, Jiayang Liu, Beibei Chen, Ziren Tang, Ningwei Ouyang, Shaofeng Liang 等

Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a large-scale and richly annotated visual question answering (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. CAF enables precise and efficient cross-modal interaction. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Experimental results on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks.

Zhenyu Gu, Yanchen Xu, Sida Huang, Yubin Guo, Hongyuan Zhang

Rectified Flow (RF) has been widely used as an effective generative model. Although RF is primarily based on probability flow Ordinary Differential Equations (ODE), recent studies have shown that injecting noise through reverse-time Stochastic Differential Equations (SDE) for sampling can achieve superior generative performance. Inspired by Positive-incentive Noise (Pi-noise), we propose an innovative generative algorithm to train Pi-noise generators, namely Rectified Noise (RN), which improves the generative performance by injecting Pi-noise into the velocity field of pre-trained RF models. After introducing the Rectified Noise pipeline, pre-trained RF models can be efficiently transformed into Pi-noise generators. We validate Rectified Noise by conducting extensive experiments across various model architectures on different datasets. Notably, we find that: (1) RF models using Rectified Noise reduce FID from10.16 to 9.05 on ImageNet-1k. (2) The models of Pi-noise generators achieve improved performance with only 0.39% additional training parameters.

Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Wei Ge, Ming Tang, Jinqiao Wang

Anomaly detection is a critical task across numerous domains and modalities, yet existing methods are often highly specialized, limiting their generalizability. These specialized models, tailored for specific anomaly types like textural defects or logical errors, typically exhibit limited performance when deployed outside their designated contexts. To overcome this limitation, we propose AnomalyMoE, a novel and universal anomaly detection framework based on a Mixture-of-Experts (MoE) architecture. Our key insight is to decompose the complex anomaly detection problem into three distinct semantic hierarchies: local structural anomalies, component-level semantic anomalies, and global logical anomalies. AnomalyMoE correspondingly employs three dedicated expert networks at the patch, component, and global levels, and is specialized in reconstructing features and identifying deviations at its designated semantic level. This hierarchical design allows a single model to concurrently understand and detect a wide spectrum of anomalies. Furthermore, we introduce an Expert Information Repulsion (EIR) module to promote expert diversity and an Expert Selection Balancing (ESB) module to ensure the comprehensive utilization of all experts. Experiments on 8 challenging datasets spanning industrial imaging, 3D point clouds, medical imaging, video surveillance, and logical anomaly detection demonstrate that AnomalyMoE establishes new state-of-the-art performance, significantly outperforming specialized methods in their respective domains.

Yiyang Gu, Bohan Wu, Yifang Qin, Jiaru Tang, Rong-Cheng Tu, Zhiping Xiao, Taian Guo, Junyu Luo, Wei Ju, Xiao Luo 等

In this paper, we study the problem of robust multi-label hashing, where label noise hinders the learning of a reliable semantic structure from data. Many existing methods rely on heuristic sample selection or consistency-based training, but lack a unified mechanism to validate and refine supervision across structural and semantic levels. Inspired by cognitive theories of human memory, we propose a novel framework called CogniTrust that unifies verifiable supervision with a triadic memory model: a) In episodic memory, feature activations are decomposed into spatial patterns that support the assessment of structural evidence and the estimation of label reliability; b) Semantic memory keeps track of class-level prototypes from structurally attentive regions to estimate the semantic plausibility of labels; c) Reconstructive memory simulates memory recall through interpolation between images using a diffusion-based mixup process, which enriches the training signals for semantically uncertain regions. These components work together, allowing supervision to be refined through the joint consideration of spatial structure and semantic information. Extensive experiments on noisy hashing benchmarks demonstrate that CogniTrust consistently outperforms a range of state-of-the-art baselines. Our results show that cognitive memory mechanisms offer a principled basis for more reliable label denoising and robust hashing.

Xianming Gu, Lihui Wang, Ying Cao, Zeyu Deng, Yingfeng Ou, Guodong Hu, Yi Chen

Multi-contrast magnetic resonance imaging (MRI) super-resolution intends to reconstruct high-resolution (HR) images from low-resolution (LR) scans by leveraging structural information present in HR reference images acquired with different contrasts. This technique enhances anatomical detail and soft tissue differentiation, which is vital for early diagnosis and clinical decision-making. However, inherent contrasts disparities between modalities pose fundamental challenges in effectively utilizing reference image textures to guide target image reconstruction, often resulting in suboptimal feature integration. To address this issue, we propose a dual-prompt expert network based on a convolutional dictionary feature decoupling (CD-DPE) strategy for multi-contrast MRI super-resolution. Specifically, we introduce an iterative convolutional dictionary feature decoupling module (CD-FDM) to separate features into cross-contrast and intra-contrast components, thereby reducing redundancy and interference. To fully integrate these features, a novel dual-prompt feature fusion expert module (DP-FFEM) is proposed. This module uses a frequency prompt to guide the selection of relevant reference features for incorporation into the target image, while an adaptive routing prompt determines the optimal method for fusing reference and target features to enhance reconstruction quality. Extensive experiments on public multi-contrast MRI datasets demonstrate that CD-DPE outperforms state-of-the-art methods in reconstructing fine details. Additionally, experiments on unseen datasets demonstrated that CD-DPE exhibits strong generalization capabilities.

Xiang Gu, Liming Lu, Xu Zheng, Anan Du, Yongbin Zhou, Shuchao Pang

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead and (2) poor generalization ability across diverse attack types. To bridge these gaps, we propose a novel yet efficient teacher-student framework, namely Multimodal Robust Prompt Distillation (MRPD) for distilling robust 3D point cloud model. It learns lightweight prompts by aligning student point cloud model's features with robust embeddings from three distinct teachers: a vision model processing depth projections, a high-performance 3D model, and a text encoder. To ensure a reliable knowledge transfer, this distillation is guided by a confidence-gated mechanism which dynamically balances the contribution of all input modalities. Notably, since the distillation is all during the training stage, there is no additional computational cost at inference. Extensive experiments demonstrate that MRPD substantially outperforms state-of-the-art defense methods against a wide range of white-box and black-box attacks, while even achieving better performance on clean data. Our work presents a new, practical paradigm for building robust 3D vision systems by efficiently harnessing multimodal knowledge.