Vanilla convolution and window-based self-attention have shown significant success in image dehazing. However, they are constrained by limited receptive fields and ignore frequency gaps between dehazed and clear images. The former hampers the modeling of global dependencies, while the latter impedes the learning of high-frequency features, leading to suboptimal performance. In this paper, we propose the Joint Spatial and Fourier Convolutional Network (JSFC-Net), which leverages Fourier transformation to simultaneously address the two aforementioned problems with low computational overhead. We introduce the Frequency-Spatial Promoted and Physical Learning Block, which extracts high-level features from the spatial domain and frequency domain in parallel. We design a simple yet effective solution that uses spatial features to promote and modulate frequency features in a multi-scale manner, achieving refinement of frequency features and addressing robustness issue caused by global sensitivity. Additionally, we present the Receptive Field Selection Module to facilitate improved fusion of spatial and frequency domain features. Finally, we introduce frequency loss to further narrow frequency gaps. Comprehensive experiments on multiple datasets demonstrate that JSFC-Net is significantly superior to SOTA dehazing methods.
论文检索
输入标题、作者或关键词，从 3,314 篇学术成果中精准定位
Remote sensing image fusion aims to reconstruct a high spatial and spectral resolution image by integrating the spatial and spectral information from multiple remote sensing sensor data. Despite the remarkable progress of deep learning-based fusion methods, most existing methods rely on manual network architecture design and hyperparameter tuning, lacking sufficient interpretability and adaptability. To address this limitation, we propose a novel neural Ordinary Differential Equation (ODE)-inspired tuning-free proximal splitting algorithm, which splits remote sensing image fusion as two optimization problems regularized by deep priors to model the fusion of spatial and spectral. Firstly, based on the physical properties of spatial and spectral information, the two problems are optimized by two proximal splitting operators to iteratively integrate spatial-spectral complementary information, eliminating or suppressing redundant information to reduce fusion errors. Secondly, considering the efficiency of neural ODE in reducing optimization error, we utilize a high-order numerical scheme to customize the proximal operator theoretically without additional handcrafted design and parameter tuning. Finally, by incorporating the numerical scheme as a solver into the proximal optimization algorithm, we derive an ODE-inspired Tuning-free Proximal Network, dubbed OTPNet, which achieves efficient and robust fusion reconstruction. Extensive experiments on nine datasets across three different remote sensing image fusion tasks show that our OTPNet outperforms existing state-of-the-art approaches, which validates the effectiveness of our method.
3D single object tracking (3D SOT) in LiDAR point clouds is essential for autonomous driving. Most existing 3D SOT methods focus on clear weather, where point clouds are more defined. However, adverse weather conditions lead to sparser and noisier point clouds, significantly degrading tracking performance and posing safety risks. In this study, we introduce UAWTrack, a universal 3D SOT model designed to perform effectively across diverse real-world weather conditions. UAWTrack comprises three key modules: 1) Voxel Feature Extraction, which mitigates the perturbations in point clouds caused by adverse weather; 2) Motion-centric Spatial-temporal Aggregation and Motion-guided Feature Fusion, capturing motion clues and sampling dense BEV motion features to address the issue of sparsity; and 3) Weather-Specific Tracker, which efficiently handles tracking in various weather conditions. To fill the gap of lacking benchmarks for 3D SOT in adverse weather, we simulate physically valid adverse weather conditions on the KITTI and NuScenes datasets, creating two benchmarks: KITTI-A and NuScenes-A. Extensive experiments demonstrate that UAWTrack achieves state-of-the-art performance under all weather conditions.
Recently, Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have shown promise in instruction following and image understanding. While these models are powerful, they have not yet been developed to comprehend the more challenging 3D geometric and physical scenes, especially when it comes to the sparse outdoor LiDAR data. In this paper, we introduce LiDAR-LLM, which takes raw LiDAR data as input and harnesses the remarkable reasoning capabilities of LLMs to gain a comprehensive understanding of outdoor 3D scenes. The central insight of our LiDAR-LLM is the reformulation of 3D outdoor scene cognition as a language modeling problem, encompassing tasks such as 3D captioning, 3D grounding, 3D question answering, etc. Specifically, due to the scarcity of 3D LiDAR-text pairing data, we introduce a three-stage training strategy and generate relevant datasets, progressively aligning the 3D modality with the language embedding of LLM. Furthermore, we design a Position-Aware Transformer (PAT) to connect the 3D encoder with the LLM, which effectively bridges the modality gap and enhances the LLM's spatial orientation comprehension of visual features. Our experiments demonstrate that LiDAR-LLM effectively comprehends a wide range of instructions related to 3D scenes, achieving a 40.9 BLEU-1 score on the 3D captioning dataset, a Grounded Captioning accuracy of 63.1%, and a BEV mIoU of 14.3%.
3D Vision Grounding (3D-VG) seeks to unravel referential language and identify targets in 3D physical world. Prevailing methods align with the 2D-VG's pipeline to pinpoint the referred object in a categorical multi-modal reasoning manner. However, the geometric complexities of 3D scenes and the nuanced syntactic structures of language, exacerbates the \textbf{granularity inconsistency} of point cloud and text features, hindering the development of 3D-VG systems in complex scenarios. Towards this issue, we propose LIBA, a Language-Instructed multi-granularity Bridge Assistant tailored for 3D-VG task. LIBA tackles this issue as follows. (1) \textit{How to establish a multi-granularity 3D vision-text feature alignment in a unified model}? We advance a bilateral Dynamic Bridge Adapter (DBA) build multi-granularity interaction of 3D vision and language backnones during feature extraction. We further develop the Language-aware Cross-scale Object Modulation (LCOM) module to integrate multi-scale point cloud features modulated by language information. (2) After aligning multi-modal features, \textit{how to fully harness language model's knowledge to bolster vision concepts understanding}? A LLM-guided Hierarchical Query Selection (LLM-HQS) module incorporates world knowledge of Large Language Model~(LLM) to ground the target referral via an Attribute-then-Relation reasoning process. In this manner, our LIBA inherits reasoning prowess and world knowledge of LLM to bridge point clouds and texts at multiple granularities. Experiments on ScanRefer and Nr3D/Sr3D benchmarks substantiate the superiority of our LIBA, trumping state-of-the-arts by a considerable margin.
Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
PDF ↗As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks.
Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images
PDF ↗Neural Radiance Fields (NeRF) have demonstrated prominent performance in novel view synthesis tasks. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene contents in low-light environments where images typically exhibit significant noise and severe color distortion. To address these challenges, we propose a novel approach, Bright-NeRF, which learns enhanced and high-quality radiance fields from multi-view low-light RAW images in an unsupervised manner. Our method simultaneously achieves color restoration, denoising, and enhanced novel view synthesis. Specifically, we leverage a physically-inspired model of the sensor's response to illumination and introduce a chromatic adaptation loss to constrain the learning of response, enabling consistent color perception of objects regardless of lighting conditions. We further utilize the RAW data's properties to expose the scene's intensity automatically. Additionally, we have collected a multi-view low-light RAW image dataset of real-world scenes to advance research in this field. Experimental results demonstrate that our proposed method significantly outperforms existing 2D and 3D approaches. Our code and dataset will be made publicly available.
Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG). Our key insight is that when humans manipulate new objects, they initially mimic the interaction patterns observed in similar objects, then progressively adjust hand-object contact. Consequently, we develop RAGG as a two-stage approach, encompassing retrieval-guided generation and structurally stable grasp refinement. In the first stage, we propose a Retrieval-Augmented Diffusion Model (ReDim), which identifies the most relevant interaction instance from a knowledge base to explicitly guide grasp generation, thereby mitigating ambiguity and bridging modality gaps to ensure semantically correct manipulation. In the second stage, we introduce a Progressive Refinement Network (PRN) with Kolmogorov-Arnold Network (KAN) layers to refine the generated coarse grasp, employing a Structural Similarity Index loss to constrain the spatial relationship between the hand and the object, thus ensuring the stability of the grasp. Extensive experiments on the OakInk and GRAB benchmarks demonstrate that RAGG achieves superior results compared to state-of-the-art approach, indicating not only better physical feasibility and controllability but also strong generalization and interpretability for unseen objects.
Enabling Large Language Models (LLMs) to comprehend the 3D physical world remains a significant challenge. Due to the lack of large-scale 3D-text pair datasets, the success of LLMs has yet to be replicated in 3D understanding. In this paper, we rethink this issue and propose a new task: 3D Data-Efficient Point-Language Understanding. The goal is to enable LLMs to achieve robust 3D object understanding with minimal 3D point cloud and text data pairs. To address this task, we introduce GreenPLM, which leverages more text data to compensate for the lack of 3D data. First, inspired by using CLIP to align images and text, we utilize a pre-trained point cloud-text encoder to map the 3D point cloud space to the text space. This mapping leaves us to seamlessly connect the text space with LLMs. Once the point-text-LLM connection is established, we further enhance text-LLM alignment by expanding the intermediate text space, thereby reducing the reliance on 3D point cloud data. Specifically, we generate 6M free-text descriptions of 3D objects, and design a three-stage training strategy to help LLMs better explore the intrinsic connections between different modalities. To achieve efficient modality alignment, we design a zero-parameter cross-attention module for token pooling. Extensive experimental results show that GreenPLM requires only 12% of the 3D training data used by existing state-of-the-art models to achieve superior 3D understanding. Remarkably, GreenPLM also achieves competitive performance using text-only data.
Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model
PDF ↗Indoor scene synthesis aims to automatically produce plausible, realistic, and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM) assist in open-vocabulary indoor scene synthesis. However, the challenge lies in converting the LLM-generated outputs into reasonable and physically feasible scene layouts. In this paper, we propose to generate hierarchically structured scene descriptions with LLM and then compute the scene layouts. Specifically, we train a hierarchy-aware network to infer the fine-grained relative positions between objects and design a divide-and-conquer optimization to solve for scene layouts. The advantages of using hierarchically structured scene representation are two-fold. First, the hierarchical structure provides a rough grounding for object arrangement, which alleviates contradictory placements with dense relations and enhances the generalization ability of the network to infer fine-grained placements. Second, it naturally supports the divide-and-conquer optimization, by first arranging the sub-scenes and then the entire scene, to more effectively solve for a feasible layout. We conduct extensive comparison experiments and ablation studies with both qualitative and quantitative evaluations to validate the effectiveness of our key designs with the hierarchically structured scene representation. Our approach can generate more reasonable scene layouts while better aligned with the user requirements and LLM descriptions. We also present open-vocabulary scene synthesis and interactive scene design results to show the strength of our approach in the applications.
Multi-focus image fusion (MFIF) enhances depth of field in photography by generating an all-in-focus image from multiple images captured at different focal lengths. While deep learning has shown promise in MFIF, most existing methods overlooked the physical properties of defocus blurring in their network design, limiting their interoperability and generalization. This paper introduces a novel framework that integrates explicit defocus blur modelling into the MFIF process, improving both interpretability and performance. Using an atom-based spatially-varying parameterized defocus blurring model, our approach calculates pixel-wise defocus descriptors and initial focused images from multi-focus source images in a scale-recurrent manner to estimate soft decision maps. Fusion is then performed using masks derived from these decision maps, with special treatment for pixels likely defocused in all source images or near boundaries of defocused/focused regions. The model is trained with a fusion loss and a cross-scale defocus estimation loss. Extensive experiments on benchmark datasets demonstrated the effectiveness of our approach.
Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging
PDF ↗In the coded aperture snapshot spectral imaging system, Deep Unfolding Networks (DUNs) have made impressive progress in recovering 3D hyperspectral images (HSIs) from a single 2D measurement. However, the inherent nonlinear and ill-posed characteristics of HSI reconstruction still pose challenges to existing methods in terms of accuracy and stability. To address this issue, we propose a Mamba-inspired Joint Unfolding Network (MiJUN), which integrates physics-embedded DUNs with learning-based HSI imaging. Firstly, leveraging the concept of trapezoid discretization to expand the representation space of unfolding networks, we introduce an accelerated unfolding network scheme. This approach can be interpreted as a generalized accelerated half-quadratic splitting with a second-order differential equation, which reduces the reliance on initial optimization stages and addresses challenges related to long-range interactions. Crucially, within the Mamba framework, we restructure the Mamba-inspired global-to-local attention mechanism by incorporating a selective state space model and an attention mechanism. This effectively reinterprets Mamba as a variant of the Transformer architecture, improving its adaptability and efficiency. Furthermore, we refine the scanning strategy with Mamba by integrating the tensor mode-k unfolding into the Mamba network. This approach emphasizes the low-rank properties of tensors along various modes, while conveniently facilitating 12 scanning directions. Numerical and visual comparisons on both simulation and real datasets demonstrate the superiority of our proposed MiJUN, and achieving overwhelming detail representation.
Visible spectrum images capture limited information from just three discrete bands, often resulting in suboptimal performance in underwater depth estimation (UDE) due to significant information loss from water absorption. In contrast, HSIs, which include hundreds of continuous bands, provide abundant spectral information that offers greater resilience against the adverse effects of water absorption. In this paper, we conduct a comprehensive study to investigate how spectral information can enhance remote sensing UDE through two key aspects: the benchmark dataset and the general framework. For the benchmark dataset, we construct a real-world hyperspectral UDE (HUDE) dataset ATR-HUDE, comprising approximately 500 synchronized hyperspectral and LiDAR data pairs collected from diverse coastal scenes and flight altitudes. Regarding the general framework, we integrate recent advances in state space models and physical imaging models to design a novel HUDE framework named HUDEMamba that estimates underwater depth using both model-driven and data-driven approaches. Experimental results on the constructed benchmark dataset validate the potential of HUDE and the effectiveness of HUDEMamba.
Hyperspectral image (HSI) reconstruction aims to restore the original 3D HSIs from the 2D hyperspectral snapshot compressive images (SCIs). The key to high-fidelity HSI reconstruction lies in designing refined spatial and spectral attention mechanisms, which are crucial for generating fine-grained representations of HSI based on the limited spatial and spectral information available in SCI. Recently, Mamba has demonstrated remarkable performance and efficiency in modeling spatial correlations. Its implicit attention mechanism generates three orders of magnitude more attention matrices than transformers, significantly raising the performance ceiling for HSI reconstruction. In this paper, we propose a novel joint SSM network named Sp3ctralMamba for HSI reconstruction. Sp3ctralMamba integrates frequency domain knowledge and physical priors to enhance reconstruction quality. Specifically, we first perform hierarchical decomposition of the 3D HSI embedding to mitigate the negative impact of distant bands on reconstruction. Next, we design a joint SSM block S3Mamba (S3MAB) to perform parallel scans of the embeddings from different bands. In addition to the conventional vanilla scan, S3MAB introduces a local scanning scheme to address the reconstruction challenges posed by the spatial sparsity of spectral information. Furthermore, a spiral scanning scheme in the frequency domain is incorporated to enhance the order correlation between different frequency signals. Finally, we introduce energy priors and structural priors to constrain the generation of spectral and spatial representations during the training process. Extensive experiments on both simulated and real datasets demonstrate that Sp3ctralMamba significantly elevates HSI reconstruction performance to a new level, surpassing SOTA methods in both quantitative and qualitative metrics.
Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions
PDF ↗Recently, deep neural networks (DNNs) have emerged as the leading approach for low-light image enhancement (LLIE). However, training these models generally requires large-scale paired datasets, which are challenging to obtain due to the labor-intensive and time-consuming nature of real-world data collection. To alleviate this issue, synthetic data are often combined with real-captured data for training. However, most existing low-light image synthesis methods are simply performed in the sRGB domain using Gamma correction or manual adjustments via Lightroom, which fail to incorporate the physical imaging prior through the image signal processing (ISP) pipeline and thus result in limited dataset size and degradation space. Consequently, LLIE methods trained on such data often exhibit some drawbacks in the results, such as inaccurate white balance and abnormal enhancement artifacts, which limit their practicality and generalizability. In this paper, we propose a practical low-light image synthesis pipeline capable of generating unlimited paired training data. Our pipeline starts with a reverse ISP model that converts sRGB images back to the unprocessed RAW domain, where we then simulate low-light degradation, noise degradation, and white balance adjustments. Finally, the degraded RAW images are processed through a forward ISP model to produce low-light sRGB images. The pipeline further employs multiple tone mapping curves and color correction matrices (CCMs) to expand the degradation space. Hence, trained with our proposed synthetic data, existing state-of-the-art (SOTA) LLIE deep models are expected to improve their performance. Extensive experiments across various datasets demonstrate that our synthetic data can indeed effectively enhance existing LLIE deep models, improving both their practicality and generalizability.
All-in-one restoration needs to implicitly distinguish between different degradation conditions and apply specific prior constraints accordingly. To fulfill this goal, our work makes the first effort to create an all-in-one restoration via unrolling from the typical maximum a-posterior optimization function. This unrolling framework naturally leads to the construction of progressively solving models, which are equivalent to a diffusion enhancer taking as input dynamically generated prompts. Under a score-based diffusion model, the prompts are integrated for propogating and updating several context-related variables, i.e. transmission map, atmospheric light map and noise or rain map progressively. Such learned prompt generation process, which simulates the nonlinear operations in the unrolled solution, is combined with linear operations owning clear physics implications to make the diffusion models well reguarlized and more effective in learning degradation-related visual priors. Experimental results demonstrate that our method achieves significant performance improvements across various image restoration tasks, realizing true all-in-one image restoration.
Deep learning-based methods have made significant progress in image dehazing. However, these methods often falter when applied to real-world hazy images, primarily due to the scarcity of paired real-world data and the limitations of current dehazing feature extractors. Toward these issues, we introduce a novel Physics Embedded Illumination Estimation (PEIE) method for adaptive real-world dehazing. Specifically, (1) we identify the limitations of the widely used Atmospheric Scattering Model and propose a new physical model, the Illumination-Adaptive Scattering Model (IASM), for more accurate illumination representation in hazy imaging; (2) we develop a robust data synthesis pipeline that leverages the physics embedded illumination estimation to generate realistic hazy images; and (3) we design an Illumination-Adaptive Dehazing Unit (IDU) to extract dehazing features consistent with our proposed IASM in the latent space. By integrating the IDU into a U-Net architecture to create IADNet, we achieve significant improvements in dehazing performance through end-to-end training on synthetic data. Extensive experiments validate the superior performance of our PEIE method, significantly surpassing the state-of-the-arts in real-world dehazing.
Event cameras, known for their low latency and high dynamic range, show great potential in pedestrian detection applications. However, while recent research has primarily focused on improving detection accuracy, the robustness of event-based visual models against physical adversarial attacks has received limited attention. For example, adversarial physical objects, such as specific clothing patterns or accessories, can exploit inherent vulnerabilities in these systems, leading to misdetections or misclassifications. This study is the first to explore physical adversarial attacks on event-driven pedestrian detectors, specifically investigating whether certain clothing patterns worn by pedestrians can cause these detectors to fail, effectively rendering them unable to detect the person. To address this, we developed an end-to-end adversarial framework in the digital domain, framing the design of adversarial clothing textures as a 2D texture optimization problem. By crafting an effective adversarial loss function, the framework iteratively generates optimal textures through backpropagation. Our results demonstrate that the textures identified in the digital domain possess strong adversarial properties. Furthermore, we translated these digitally optimized textures into physical clothing and tested them in real-world scenarios, successfully demonstrating that the designed textures significantly degrade the performance of event-based pedestrian detection models. This work highlights the vulnerability of such models to physical adversarial attacks.
DigitalLLaVA: Incorporating Digital Cognition Capability for Physical World Comprehension in Multimodal LLMs
PDF ↗Multimodal Large Language Models (MLLMs) have shown remarkable cognitive capabilities in various cross-modal tasks.However, existing MLLMs struggle with tasks that require physical digital cognition, such as accurately reading an electric meter or pressure gauge. This limitation significantly reduces their effectiveness in practical applications like industrial monitoring and home energy management, where digital sensors are not feasible. For humans, physical digits are artificially defined quantities presented on specific carriers, which require training to recognize. As existing MLLMs are only pre-trained in the manner of object recognition, they fail to comprehend the relationship between digital carriers and their reading. To this end, referring to human behavior, we propose a novel DigitalLLaVA method to explicitly inject digital cognitive abilities into MLLMs in a two-step manner. In the first step, to improve the MLLM's understanding of physical digit carriers, we propose a digit carrier mapping method. This step utilizes object-level text-image pairs to enhance the model's comprehension of objects containing physical digits. For the second step, unlike previous methods that rely on sequential digital prediction or digit regression, we propose a 32 bit floating point simulation approach that treats digit prediction as a whole. Using digit-level text-image pairs, we train three float heads to predict 32-bit floating-point numbers using 0/1 binary classification. This step significantly reduces the search space, making the prediction process more robust and straightforward. Being simple but effective, our method can identify very precise metrics (i.e., accurate to ±0.001) and provide floating-point results, showing its applicability in digital carrier domains.
KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models
PDF ↗Adversarial patches pose a significant threat to computer vision models' integrity, decreasing the accuracy of various tasks, including object detection (OD). Most existing OD defenses exhibit a trade-off between enhancing the model's adversarial robustness and maintaining its performance on benign images. We propose KDAT (knowledge distillation with adversarial tuning), a novel mechanism that enhances the robustness of an OD model without compromising its performance on benign images or its inference time. Our method combines the knowledge distillation (KD) technique with the adversarial tuning concept to teach the model to match the predictions of adversarial images with those of their corresponding benign ones. To match these predictions, we designed four unique loss components, allowing the student model to effectively distill the knowledge of different features from various parts of the teacher model. Our extensive evaluation on the COCO and INRIA datasets demonstrates KDAT's ability to improve the performance of Faster R-CNN and DETR on benign images by 2-4 mAP% and adversarial examples by 10-15 mAP%, outperforming other state-of-the-art (SOTA) defenses. Furthermore, our additional physical evaluation on the Superstore dataset demonstrates KDAT's SOTA adversarial robustness against printed patches (improvement of 22 mAP% compared to the undefended model).