论文检索

Qixian Hao, Shaozhang Niu, Jiwei Zhang, Kai Wang

Generative Image Tampering (GIT), due to its high diversity and realism, poses a significant challenge to traditional image tampering localization techniques. Consequently, this paper introduces a denoising diffusion probabilistic model-based DcDsDiff, which comprises a Dual-View Conditional Network (DVCN) and a Dual-Stream Denoising Network (DSDN). DVCN provides clues about the tampered areas. It extracts tampering features in the high-frequency view and integrates them with spatial domain features using attention mechanisms. DSDN jointly generates mask image and detail image, enhancing the generalization capability of the model against new tampering forms through iterative denoising. A multi-stream interaction mechanism enables the two generative tasks to promote each other, prompting the model to generate localization results that are rich in detail and complete. Experiments show that DcDsDiff outperforms mainstream methods in accurate localization, generalization, extensibility, and robustness. Code page: https://github.com/QixianHao/DcDsDiff-and-GIT10K.

Mingce Guo, Jingxuan He, Yufei Yin, Zhangye Wang, Shengeng Tang, Lechao Cheng

Text-driven video editing powered by generative diffusion models holds significant promise for applications spanning film production, advertising, and beyond. However, the limited expressiveness of pre-trained word embeddings often restricts nuanced edits, especially when targeting novel concepts with specific attributes. In this work, we present a novel Concept-Augmented Textual Inversion (CATI) framework that flexibly integrates new object information from user-provided concept videos. By fine-tuning only the V (Value) projection in attention via Low-Rank Adaptation (LoRA), our approach preserves the original attention distribution of the diffusion model while efficiently incorporating external concept knowledge. To further stabilize editing results and mitigate the issue of attention dispersion when prompt keywords are modified, we introduce a Dual Prior Supervision (DPS) mechanism. DPS supervises cross-attention between the source and target prompts, preventing undesired changes to non-target areas and improving the fidelity of novel concepts. Extensive evaluations demonstrate that our plug-and-play solution not only maintains spatial and temporal consistency but also outperforms state-of-the-art methods in generating lifelike and stable edited videos. The source code is publicly available at https://guomc9.github.io/STIVE-PAGE/.

Weikang Gu, Mingyue Han, Li Xue, Heng Dong, Changcai Yang, Riqing Chen, Lifang Wei

The accurate identification of high-quality correspondences is a prerequisite task in feature-based point cloud registration. However, it is extremely challenging to handle the fusion of local and global features due to feature redundancy and complex spatial relationships. Given that Gestalt principles provide key advantages in analyzing local and global relationships, we propose a novel Gestalt-guided Parallel Interaction Network via orthogonal geometric consistency (GPI-Net) in this paper. It utilizes Gestalt principles to facilitate complementary communication between local and global information. Specifically, we introduce an orthogonal integration strategy to optimally reduce redundant information and generate a more compact global structure for high-quality correspondences. To capture geometric features in correspondences, we leverage a Gestalt Feature Attention (GFA) block through a hybrid utilization of self-attention and cross-attention mechanisms. Furthermore, to facilitate the integration of local detail information into the global structure, we design an innovative Dual-path Multi-Granularity parallel interaction aggregation (DMG) block to promote information exchange across different granularities. Extensive experiments on various challenging tasks demonstrate the superior performance of our proposed GPI-Net in comparison to existing methods. The code will be released at https://github.com/XXX/GPI-Net.

Hongjie Gu, Jinlong Fan, Liang Zheng, Jing Zhang, Yuxiang Yang

3D visual grounding aims to localize target objects in point clouds based on free-form natural language, which often describes both target and reference objects. Effective alignment between visual and text features is crucial for this task. However, existing two-stage methods that rely solely on object-level features can yield suboptimal accuracy, while one-stage methods that align only point-level features can be prone to noise. In this paper, we propose DDPA-3DVG, a novel framework that progressively aligns visual locations and language descriptions at multiple granularities. Specifically, we decouple natural language descriptions into distinct representations of target objects, reference objects, and their mutual relationships, while disentangling 3D scenes into object-level, voxel-level, and point-level features. By progressively fusing these dual-decoupled features from coarse to fine, our method enhances cross-modal alignment and achieves state-of-the-art performance on three challenging benchmarks—ScanRefer, Nr3D, and Sr3D. The code will be released at https://github.com/HDU-VRLab/DDPA-3DVG.

Zhihao Gong, Lian Wu, Yong Xu

Visible-infrared person re-identification (VIReID) provides a solution for ReID tasks in 24-hour scenarios; however, significant challenges persist in achieving satisfactory performance due to the substantial discrepancies between visible (VIS) and infrared (IR) modalities. Existing methods inadequately leverage information from different modalities, primarily focusing on digging distinguishing features from modality-shared information while neglecting modality-specific details. To fully utilize differentiated minutiae, we propose a Base-Detail Feature Learning Framework (BDLF) that enhances the learning of both base and detail knowledge, thereby capitalizing on both modality-shared and modality-specific information. Specifically, the proposed BDLF mines detail and base features through a lossless detail feature extraction module and a complementary base embedding generation mechanism, respectively, supported by a novel correlation restriction method that ensures the features gained by BDLF enrich both detail and base knowledge across VIS and IR features. Comprehensive experiments conducted on the SYSU-MM01, RegDB, and LLCM datasets validate the effectiveness of BDLF.

Wenxuan Ge, Peng Huang, Rui Yan, Hongyu Qu, Guosen Xie, Xiangbo Shu

Adapting pre-trained vision-language models to downstream tasks has emerged as a novel paradigm for zero-shot learning. Existing test-time adaptation (TTA) methods such as TPT attempt to fine-tune visual or textual representations to accommodate downstream tasks but still require expensive optimization costs. To this end, Training-free Dynamic Adapter (TDA) maintains a cache containing visual features for each category in a parameter-free manner and measures sample confidence based on prediction entropy of test samples. Inspired by TDA, this work aims to develop the first training-free adapter for zero-shot video classification. Capturing the intrinsic temporal relationships within video data to construct and maintain the video cache is key to extending TDA to the video domain. In this work, we propose a reliable and diverse Hierarchical Adapter for zero-shot video classification, which consists of Frame-level Cache Refiner and Video-level Cache Updater. Before each video sample enters the corresponding cache, it needs to be refined at frame level based on prediction entropy and temporal probability difference. Due to the limited capacity of the cache, we update the cache during inference based on the principle of diversity. Experiments on four popular video classification benchmarks demonstrate the effectiveness of Hierarchical Adapter. The code is available at https://github.com/Gwxer/Hierarchical-Adapter.

Bulat Gabdullin, Nina Konovalova, Nikolay Patakin, Dmitry Senushkin, Anton Konushin

Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by leveraging priors from internet-scale datasets, with recent studies showing state-of-the-art results using fine-tuned text-to-image diffusion models, there is still room for improvement. Notably, autoregressive generative approaches, particularly Visual AutoRegressive modeling, have demonstrated superior results compared to diffusion models in conditioned image synthesis, while offering faster inference times. In this work, we apply Visual Autoregressive Transformer (VAR) to the monocular depth estimation problem. However, the conventional GPT-2-style training procedure (teacher forcing) inherited by VAR yields suboptimal results for depth estimation. To address this limitation, we introduce DepthART - a novel training method formulated as a Depth Autoregressive Refinement Task. Unlike traditional VAR training with static inputs and targets, our method implements a dynamic target formulation based on model outputs, enabling self-refinement. By utilizing the model's own predictions as inputs instead of ground truth token maps during training, we frame the objective as residual minimization, effectively reducing the discrepancy between training and inference procedures. Our experimental results demonstrate that the proposed training approach significantly enhances the performance of VAR in depth estimation tasks. When trained on Hypersim dataset using our approach, the model achieves superior results across multiple unseen benchmarks compared to existing generative and discriminative baselines.

Weiwei Feng, Nanqing Xu, Tengfei Liu, Weiqiang Wang

Due to the high similarity between camouflaged instances and the surroundings and the widespread camouflage-like scenarios, the recently proposed camouflaged instance segmentation (CIS) is a challenging and relevant task. Previous approaches achieve some progress on CIS, while many overlook camouflaged objects’ color and contour nature and then decide on each candidate instinctively. In this paper, we contribute a Mixture-of-Queries Transformer (MoQT) in an end-to-end manner for CIS based on two key designs (a Frequency Enhancement Feature Extractor and a Mixture-of-Queries Decoder). First, the Frequency Enhancement Feature Extractor is responsible for capturing the camouflaged clues in the frequency domain. To expose camouflaged instances, the extractor enhances the effectiveness of contour, eliminates the interference color, and obtains suitable features simultaneously. Second, a Mixture-of-Queries Decoder utilizes multiple newly initialized experts of queries (a group of queries considered an expert) in each layer for spotting camouflaged characteristics with cooperation. These experts collaborate to generate outputs with the mixture-of-queries mechanism, refined hierarchically to a fine-grained level for more accurate instance masks. Coupling these two components enables MoQT to use multiple experts to integrate effective clues of camouflaged objects in both spatial and frequency domains. Extensive experimental results demonstrate our MoQT outperforms 19 state-of-the-art CIS approaches on both COD10K and NC4K datasets.

Weijia Feng, Yichen Zhu, Ruojia Zhang, Chenyang Wang, Fei Ma, Xiaobao Wang, Xiaobai Li

Owing to its rapid progress and broad application prospects, few-shot action recognition has attracted considerable interest. However, current methods are predominantly based on limited single-modal data, which does not fully exploit the potential of multimodal information. This paper presents a novel framework that actively identifies reliable modalities for each sample using task-specific contextual cues, thus significantly improving recognition performance. Our framework integrates an Active Sample Inference (ASI) module, which utilizes active inference to predict reliable modalities based on posterior distributions and subsequently organizes them accordingly. Unlike reinforcement learning, active inference replaces rewards with evidence-based preferences, making more stable predictions. Additionally, we introduce an active mutual distillation module that enhances the representation learning of less reliable modalities by transferring knowledge from more reliable ones. Adaptive multimodal inference is employed during the meta-test to assign higher weights to reliable modalities. Extensive experiments across multiple benchmarks demonstrate that our method significantly outperforms existing approaches.

Wei Feng, Kangrui Ye, Qi Zhang, Qian Zhang, Nan Li

Gaussian splatting techniques have recently revolutionized outdoor scene decomposition and relighting through multi-view images. However, achieving high rendering quality still requires a fixed lighting condition among all input views, which is costly or even impractical to capture in outdoor scenes. In this paper, we propose outdoor scene decomposition and relighting with 2D Gaussian splatting (OSDR-GS), a novel inverse rendering strategy under outdoor changing and unknown lighting conditions. Firstly, we present a lighting-based group learning framework that categorizes input images into multiple lighting groups, to learn the separate lighting from each group individually. Secondly, OSDR-GS introduces a fine-grained outdoor lighting component to represent sun-light and sky-light, respectively, which are also adjusted via the correlative exposure factors adaptively. Finally, we construct a visibility-driven shadow module to characterize the nuanced interplay of light and occlusion realistically, for eliminating the uncertainty of dark pixels on lighting-based group learning. Extensive experiments on multiple challenging outdoor datasets validate the effectiveness of OSDR-GS, which achieves the state-of-the-art performance in changing lighting scene inverse rendering.

Zhirui Fang, Yi Li, Xin Xie, Chengyan Li, Yanqing Guo

Style transfer is a challenging task in computer vision, aiming to blend the stylistic features of one image with the content of another while preserving the content details. Traditional methods often face challenges in terms of computational efficiency and fine-grained content preservation. In this paper, we propose a novel feature modulation mechanism based on parameterized normalization, where the modulation parameters for content and style features are learned using a dual convolution network (BiConv). These parameters adjust the mean and standard deviation of the features, improving both the stability and quality of the style transfer process. To achieve fast inference, we introduce an efficient acceleration technique by leveraging a row and column weighted attention matrix. In addition, we incorporate a contrastive learning scheme to align the local features of the content and the stylized images, improving the fidelity of the generated output. Experimental results demonstrate that our method significantly improves the inference speed and the quality of style transfer while preserving content details, outperforming existing approaches based on both convolution and diffusion.

Siyan Fang, Yuntao Wang, Jinpu Zhang, Ziwen Li, Yuehuan Wang

Existing image reflection removal methods struggle to handle complex reflections. Accurate language descriptions can help the model understand the image content to remove complex reflections. However, due to blurred and distorted interferences in reflected images, machine-generated language descriptions of the image content are often inaccurate, which harms the performance of language-guided reflection removal. To address this, we propose the Adaptive Language-Aware Network (ALANet) to remove reflections even with inaccurate language inputs. Specifically, ALANet integrates both filtering and optimization strategies. The filtering strategy reduces the negative effects of language while preserving its benefits, whereas the optimization strategy enhances the alignment between language and visual features. ALANet also utilizes language cues to decouple specific layer content from feature maps, improving its ability to handle complex reflections. To evaluate the model's performance under complex reflections and varying levels of language accuracy, we introduce the Complex Reflection and Language Accuracy Variance (CRLAV) dataset. Experimental results demonstrate that ALANet surpasses state-of-the-art methods for image reflection removal. The code and dataset are available at https://github.com/fashyon/ALANet.

Chenghao Fang, Jianqing Liang, Jiye Liang, Hangkun Wang, Kaixuan Yao, Feilong Cao

Multi-modal point cloud completion, which utilizes a complete image and a partial point cloud as input, is a crucial task in 3D computer vision. Previous methods commonly employ a cross-attention mechanism to fuse point clouds and images. However, these approaches often fail to fully leverage image information and overlook the intrinsic geometric details of point clouds that could complement the image modality. To address these challenges, we propose an interleaved attention enhanced Transformer (IAET) with three main components, i.e., token embedding, bidirectional token supplement, and coarse-to-fine decoding. IAET incorporates a novel interleaved attention mechanism to enable bidirectional information supplementation between the point cloud and image modalities. Additionally, to maximize the use of the supplemented image information, we introduce a view-guided upsampling module that leverages image tokens as queries to guide the generation of detailed point cloud structures. Extensive experiments demonstrate the effectiveness of IAET, highlighting its state-of-the-art performance on multi-modal point cloud completion benchmarks in various scenarios. The source code is freely accessible at https://github.com/doldolOuO/IAET.

Shaojun E, Yuchen Yang, Jiaheng Wu, Yan Zhang, Tiejun Zhao, Ziyan Chen

In the latest advancements in multimodal learning, effectively addressing the spatial and semantic losses of visual data after encoding remains a critical challenge. This is because the performance of large multimodal models is positively correlated with the coupling between visual encoders and large language models. Existing approaches often face issues such as vector gaps or semantic disparities, resulting in information loss during the propagation process. To address these issues, we propose MAGE (Multimodal Alignment and Generation Enhancement), a novel framework that bridges the semantic spaces of vision and text through an innovative alignment mechanism. By introducing the Intelligent Alignment Network (IAN), MAGE achieves dimensional and semantic alignment. To reduce the gap between synonymous heterogeneous data, we employ a training strategy that combines cross-entropy and mean squared error, significantly enhancing the alignment effect. Moreover, to enhance MAGE’s “Any-to-Any” capability, we developed a fine-tuning dataset for multimodal tool-calling instructions to expand the model’s output capability boundaries. Finally, our proposed multimodal large model architecture, MAGE, achieved significantly better performance compared to similar works across various evaluation benchmarks, including MME, MMBench, and SEED. Complete code and appendix are available at: https://github.com/GTCOM-NLP/MAGE

Xiangcheng Du, Zhao Zhou, Yanlong Wang, Yingbin Zheng, Xingjiao Wu, Peizhu Gong, Cheng Jin

Recent data-driven image colorization methods have leveraged pre-trained Text-to-Image (T2I) diffusion models as generative prior, while still suffering from unsatisfactory and inaccurate semantic-level color control. To address these issues, we propose a Semantic Adaptation method (SeAda) that enhances the prior while considering the semantic discrepancy between color and grayscale image pairs. The SeAda employs a semantic adapter to produce refined semantic embeddings and a controlled T2I diffusion model to create reasonably colored images. Specifically, the semantic adapter transfers the embedding from grayscale to color domain, while the diffusion model utilizes the refined embedding and prior knowledge to achieve realistic and diverse results. We also design a three-staged training strategy to improve semantic comprehension and prior integration for further performance improvement. Extensive experiments on public datasets demonstrate that our method outperforms existing state-of-the-art techniques, yielding superior performance in image colorization.

Chenghu Du, Junyin Wang, Kai Liu, Shengwu Xiong, Yi Rong

A good virtual try-on model should introduce minimal redundant conditional information to avoid instability and increase inference efficiency. Existing methods rely on inpainting masks to guide the generation of the object, but the masks, generated by unstable human parsers, often produce unreliable results with fabric residues due to wrong segmentation. Moreover, large mask regions can lose spatial structure and identity information, requiring extra conditional inputs to compensate, which increases model instability and reduces efficiency. To tackle the problem, we present a novel Mask-Free virtual Try-ON (MFTON) framework. Specifically, we propose a mask-free strategy to eliminate all denoising conditions except for clothing and person images, thereby directly extracting spatial structure and identity information from the person image to improve efficiency and reduce instability. Additionally, to optimize the generated clothing regions, we propose a clothing texture-aware attention mechanism to enable the model to focus on texture generation with significant visual differences. We then introduce a geometric detail capture loss to further enable the model to capture more high-frequency information. Finally, we propose an appearance consistency inference method to reduce the initial randomness of the sampling process significantly. Extensive experiments on popular datasets demonstrate that our method outperforms state-of-the-art virtual try-on methods.

Neng Dong, Shuanglin Yan, Liyan Zhang, Jinhui Tang

Visible-infrared person re-identification (VIReID) retrieves pedestrian images with the same identity across different modalities. Existing methods learn visual features solely from images, failing to align them into the modality-invariant semantic space. In this paper, we propose a novel framework, termed Richer Semantics, Better Alignment (RSBA), to align visual features with explicit and enriched semantics. Specifically, we first develop an Explicit Semantics-Guided Feature Alignment (ESFA) module, which supplements textual descriptions for cross-modality images and aligns image-text pairs within each modality, alleviating the distribution discrepancy of visual features. We then devise a Consistent Similarity-Guided Indirect Alignment (CSIA) module, which constrains the similarity between intra-modality image-text pairs to be consistent with that between inter-modality text-text pairs, indirectly aligning visual features with cross-modality semantics. Furthermore, we design a Cross-View Semantics Compensation (CVSC) module, which integrates multi-view texts and improves the image-text matching of one-to-one in ESFA and CSIA to one-to-many, further strengthening the alignment of visual features within the semantic space. Extensive experimental results on three public datasets demonstrate the effectiveness and superiority of our proposed RSBA.

Chunlai Dong, Haochao Ying, Qibo Qiu, Jinhong Wang, Danny Chen, Jian Wu

Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord.

Zhaodong Ding, Chenglong Li, Shengqing Miao, Jin Tang

RGBT tracking is to localize the predefined targets in video sequences by effectively leveraging the information from both visible light (RGB) and thermal infrared (TIR) modalities. However, the quality of different modalities changes dynamically in complex scenes, and effectively perceiving modal quality for multimodal fusion remains a significant challenge. To address this challenge, we propose to employ the reliability of initial template to explore the uncertainty across different modalities, and design a novel template-based uncertainty computation framework for robust multimodal fusion in RGBT tracking. In particular, we introduce an Uncertainty-aware Multimodal Fusion Module (UMFM), which constructs the uncertainty of each modality by leveraging the correlation between the template and search region in the Subjective Logic framework, aiming to achieve robust multimodal fusion. In addition, existing methods focus on dynamic template update while overlooking the potential role of a reliable initial template in the template updating process.To this end, we design a simple yet effective Contrastive Template Update Module (CTUM) to assess the reliability of the new template by comparing its quality with that of the initial template. Extensive experiments suggest that our method outperforms existing approaches on four RGBT tracking benchmarks.

Zeyu Ding, Jiaqi Zhao, Yong Zhou, Wen-liang Du, Hancheng Zhu, Rui Yao

Oriented object detection has advanced with the development of convolutional neural networks (CNNs) and transformers. However, modern detectors still rely on predefined object candidates, such as anchors in CNN-based methods or queries in transformer-based methods, which struggle to capture spatial information effectively. To address the limitations, we propose GSDet, a novel framework that formulates oriented object detection as Gaussian splatting. Specifically, our approach performs detection within a 3D feature space constructed from image features, where 3D Gaussians are employed to represent oriented objects. These 3D Gaussians are projected onto the image plane to form 2D Gaussians, which are then transformed into oriented boxes. Furthermore, we optimize the mean, anisotropic covariance, and confidence scores of these randomly initialized 3D Gaussians, using a decoder that incorporates 3D Gaussian sampling. Moreover, our method exhibits flexibility, enabling adaptive control and a dynamic number of Gaussians during inference. Experiments on 3 datasets indicate that GSDet achieves AP50 gains of 0.7% on DIOR-R, 0.3% on DOTA-v1.0, and 0.55% on DOTA-v1.5 when evaluated with adaptive control and outperforms mainstream detectors.