IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision最新文献

ChartQA-X: Generating Explanations for Visual Chart Reasoning. ChartQA-X：生成可视化图表推理的解释。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2026-03-01 Epub Date: 2026-05-05 DOI: 10.1109/wacv61042.2026.00624

Shamanthak Hegde, Pooyan Fazli, Hasti Seifi

{"title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning.","authors":"Shamanthak Hegde, Pooyan Fazli, Hasti Seifi","doi":"10.1109/wacv61042.2026.00624","DOIUrl":"10.1109/wacv61042.2026.00624","url":null,"abstract":"The ability to explain complex information from chart images is vital for effective data-driven decision-making. In this work, we address the challenge of generating detailed explanations alongside answering questions about charts. We present ChartQA-X, a comprehensive dataset comprising 30,799 chart samples across four chart types, each paired with contextually relevant questions, answers, and explanations. Explanations are generated and selected based on metrics such as faithfulness, informativeness, coherence, and perplexity. Our human evaluation with 245 participants shows that model-generated explanations in ChartQA-X surpass human-written explanations in accuracy and logic and are comparable in terms of clarity and overall quality. Moreover, models fine-tuned on ChartQA-X show substantial improvements across various metrics, including absolute gains of up to 24.57 points in explanation quality, 18.96 percentage points in question-answering accuracy, and 14.75 percentage points on unseen benchmarks for the same task. By integrating explanatory narratives with answers, our approach enables agents to convey complex visual information more effectively, improving comprehension and greater trust in the generated responses.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2026 ","pages":"6453-6463"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13166121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147936056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model. 棕榈+：利用深度基础模型的模块化基于图像的平面图定位。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2026-03-01 Epub Date: 2026-05-05 DOI: 10.1109/wacv61042.2026.00684

Yunqian Cheng, Benjamin Princen, Roberto Manduchi

{"title":"PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model.","authors":"Yunqian Cheng, Benjamin Princen, Roberto Manduchi","doi":"10.1109/wacv61042.2026.00684","DOIUrl":"10.1109/wacv61042.2026.00684","url":null,"abstract":"Indoor localization in GPS-denied environments is crucial for applications like emergency response and assistive navigation. Vision-based methods such as PALMS enable infrastructure-free localization using only a floor plan and a stationary scan, but are limited by the short range of smartphone LiDAR and ambiguity in indoor layouts. We propose PALMS+, a modular, image-based system that addresses these challenges by reconstructing scale-aligned 3D point clouds from posed RGB images using a foundation monocular depth estimation model (Depth Pro), followed by geometric layout matching via convolution with the floor plan. PALMS+ outputs a posterior over the location and orientation, usable for direct or sequential localization. Evaluated on the Structured3D and a custom campus dataset consisting of 80 observations across four large campus buildings, PALMS+ outperforms PALMS and F3Loc in stationary localization accuracy-without requiring any training. Furthermore, when integrated with a particle filter for sequential localization on 33 real-world trajectories, PALMS+ achieved lower localization errors compared to other methods, demonstrating robustness for camera-free tracking and its potential for infrastructure-free applications. Code and data are available at https://github.com/Head-inthe-Cloud/PALMS-Plane-based-Accessible-Indoor-Localization-Using-Mobile-Smartphones.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2026 ","pages":"7084-7093"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13155413/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Anatomically-guided masked autoencoder pre-training for aneurysm detection. 解剖导向的面罩式自编码器预训练用于动脉瘤检测。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2026-01-01 Epub Date: 2026-05-05 DOI: 10.1109/wacv61042.2026.00552

Alberto M Ceballos Arroyo, Jisoo Kim, Chu-Hsuan Lin, Lei Qin, Geoffrey S Young, Huaizu Jiang

{"title":"Anatomically-guided masked autoencoder pre-training for aneurysm detection.","authors":"Alberto M Ceballos Arroyo, Jisoo Kim, Chu-Hsuan Lin, Lei Qin, Geoffrey S Young, Huaizu Jiang","doi":"10.1109/wacv61042.2026.00552","DOIUrl":"10.1109/wacv61042.2026.00552","url":null,"abstract":"Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it difficult to develop such solutions using typical supervised learning frameworks. In this work, we propose a novel pre-training strategy using more widely available unannotated head CT scan data to pre-train a 3D Vision Transformer model prior to fine-tuning for the aneurysm detection task. Specifically, we modify masked auto-encoder (MAE) pre-training in the following ways: we use a factorized self-attention mechanism to make 3D attention computationally viable, we restrict the masked patches to areas near arteries to focus on areas where aneurysms are likely to occur, and we reconstruct not only CT scan intensity values but also artery distance maps, which describe the distance between each voxel and the closest artery, thereby enhancing the backbone's learned representations. Compared with SOTA aneurysm detection models, our approach gains +2-7% absolute Sensitivity at a false positive rate of 0.5. Code and weights are available at: https://github.com/alceballosa/aneurysm-mae.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2026 ","pages":"5693-5694"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13335401/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148439299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders. ARD-VAE：一种发现变分自编码器相关潜在维度的统计公式。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00096

Surojit Saha, Sarang Joshi, Ross Whitaker

{"title":"ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders.","authors":"Surojit Saha, Sarang Joshi, Ross Whitaker","doi":"10.1109/wacv61041.2025.00096","DOIUrl":"10.1109/wacv61041.2025.00096","url":null,"abstract":"The variational autoencoder (VAE) [19, 41] is a popular, deep, latent-variable model (DLVM) due to its simple yet effective formulation for modeling the data distribution. Moreover, optimizing the VAE objective function is more manageable than other DLVMs. The bottleneck dimension of the VAE is a crucial design choice, and it has strong ramifications for the model's performance, such as finding the hidden explanatory factors of a dataset using the representations learned by the VAE. However, the size of the latent dimension of the VAE is often treated as a hyperparameter estimated empirically through trial and error. To this end, we propose a statistical formulation to discover the relevant latent factors required for modeling a dataset. In this work, we use a hierarchical prior in the latent space that estimates the variance of the latent axes using the encoded data, which identifies the relevant latent dimensions. For this, we replace the fixed prior in the VAE objective function with a hierarchical prior, keeping the remainder of the formulation unchanged. We call the proposed method the automatic relevancy detection in the variational autoencoder (ARD-VAE). We demonstrate the efficacy of the ARD-VAE on multiple benchmark datasets in finding the relevant latent dimensions and their effect on different evaluation metrics, such as FID score and disentanglement analysis.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"889-898"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12747167/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145866782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Aperture Transformers for 3D (MAT3D) Segmentation of Clinical and Microscopic Images. 多孔径变压器用于临床和显微图像的三维分割。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00427

Muhammad Sohaib, Siyavash Shabani, Sahar A Mohammed, Garrett Winkelmaier, Bahram Parvin

{"title":"Multi-Aperture Transformers for 3D (MAT3D) Segmentation of Clinical and Microscopic Images.","authors":"Muhammad Sohaib, Siyavash Shabani, Sahar A Mohammed, Garrett Winkelmaier, Bahram Parvin","doi":"10.1109/wacv61041.2025.00427","DOIUrl":"10.1109/wacv61041.2025.00427","url":null,"abstract":"3D segmentation of biological structures is critical in biomedical imaging, offering significant insights into structures and functions. This paper introduces a novel segmentation of biological images that couples Multi-Aperture representation with Transformers for 3D (MAT3D) segmentation. Our method integrates the global context-awareness of Transformer networks with the local feature extraction capabilities of Convolutional Neural Networks (CNNs), providing a comprehensive solution for accurately delineating complex biological structures. First, we evaluated the performance of the proposed technique on two public clinical datasets of ACDC and Synapse multi-organ segmentation, rendering superior Dice scores of 93.34±0.05 and 89.73±0.04, respectively, with fewer parameters compared to the published literature. Next, we assessed the performance of our technique on an organoid dataset comprising four breast cancer subtypes. The proposed method achieved a Dice 95.12±0.02 and a PQ score of 97.01±0.01, respectively. MAT3D also significantly reduces the parameters to 40 million. The code is available on https://github.com/sohaibcs1/MAT3D.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"4352-4361"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12040328/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144047757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images. 基于生成模型的改进红外图像少镜头语义分割融合。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00535

Junno Yun, Mehmet Akçakaya

{"title":"Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images.","authors":"Junno Yun, Mehmet Akçakaya","doi":"10.1109/wacv61041.2025.00535","DOIUrl":"10.1109/wacv61041.2025.00535","url":null,"abstract":"Infrared (IR) imaging is commonly used in various scenarios, including autonomous driving, fire safety and defense applications. Thus, semantic segmentation of such images is of great interest. However, this task faces several challenges, including data scarcity, differing contrast and input channel number compared to natural images, and emergence of classes not represented in databases in certain scenarios, such as defense applications. Few-shot segmentation (FSS) provides a framework to overcome these issues by segmenting query images using a few labeled support samples. However, existing FSS models for IR images require paired visible RGB images, which is a major limitation since acquiring such paired data is difficult or impossible in some applications. In this work, we develop new strategies for FSS of IR images by using generative modeling and fusion techniques. To this end, we propose to synthesize auxiliary data to provide additional channel information to complement the limited contrast in the IR images, as well as IR data synthesis for data augmentation. Here, the former helps the FSS model to better capture the relationship between the support and query sets, while the latter addresses the issue of data scarcity. Finally, to further improve the former aspect, we propose a novel fusion ensemble module for integrating the two different modalities. Our methods are evaluated on different IR datasets, and improve upon the state-of-the-art (SOTA) FSS models.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"5479-5488"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12790678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145960984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network. Sli2Vol+：基于目标估计导向的对应流网络分割3D医学图像。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00357

Delin An, Pengfei Gu, Milan Sonka, Chaoli Wang, Danny Z Chen

{"title":"Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network.","authors":"Delin An, Pengfei Gu, Milan Sonka, Chaoli Wang, Danny Z Chen","doi":"10.1109/wacv61041.2025.00357","DOIUrl":"10.1109/wacv61041.2025.00357","url":null,"abstract":"Deep learning (DL) methods have shown remarkable successes in medical image segmentation, often using large amounts of annotated data for model training. However, acquiring a large number of diverse labeled 3D medical image datasets is highly difficult and expensive. Recently, mask propagation DL methods were developed to reduce the annotation burden on 3D medical images. For example, Sli2Vol [59] proposed a self-supervised framework (SSF) to learn correspondences by matching neighboring slices via slice reconstruction in the training stage; the learned correspondences were then used to propagate a labeled slice to other slices in the test stage. But, these methods are still prone to error accumulation due to the inter-slice propagation of reconstruction errors. Also, they do not handle discontinuities well, which can occur between consecutive slices in 3D images, as they emphasize exploiting object continuity. To address these challenges, in this work, we propose a new SSF, called Sli2Vol+, for segmenting any anatomical structures in 3D medical images using only a single annotated slice per training and testing volume. Specifically, in the training stage, we first propagate an annotated 2D slice of a training volume to the other slices, generating pseudo-labels (PLs). Then, we develop a novel Object Estimation Guided Correspondence Flow Network to learn reliable correspondences between consecutive slices and corresponding PLs in a self-supervised manner. In the test stage, such correspondences are utilized to propagate a single annotated slice to the other slices of a test volume. We demonstrate the effectiveness of our method on various medical image segmentation tasks with different datasets, showing better generalizability across different organs, modalities, and modals. Code is available at https://github.com/adlsn/Sli2VolPlus.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"3624-3634"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12459605/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145152049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CUNSB-RFIE: Context-aware Unpaired Neural Schrödinger Bridge in Retinal Fundus Image Enhancement. 上下文感知的未配对神经Schrödinger桥在视网膜眼底图像增强中的应用。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00442

Xuanzhao Dong, Vamsi Krishna Vasa, Wenhui Zhu, Peijie Qiu, Xiwen Chen, Yi Su, Yujian Xiong, Zhangsihao Yang, Yanxi Chen, Yalin Wang

{"title":"CUNSB-RFIE: Context-aware Unpaired Neural Schrödinger Bridge in Retinal Fundus Image Enhancement.","authors":"Xuanzhao Dong, Vamsi Krishna Vasa, Wenhui Zhu, Peijie Qiu, Xiwen Chen, Yi Su, Yujian Xiong, Zhangsihao Yang, Yanxi Chen, Yalin Wang","doi":"10.1109/wacv61041.2025.00442","DOIUrl":"10.1109/wacv61041.2025.00442","url":null,"abstract":"Retinal fundus photography is significant in diagnosing and monitoring retinal diseases. However, systemic imperfections and operator/patient-related factors can hinder the acquisition of high-quality retinal images. Previous efforts in retinal image enhancement primarily relied on GANs, which are limited by the trade-off between training stability and output diversity. In contrast, the Schrödinger Bridge (SB), offers a more stable solution by utilizing Optimal Transport (OT) theory to model a stochastic differential equation (SDE) between two arbitrary distributions. This allows SB to effectively transform low-quality retinal images into their high-quality counterparts. In this work, we leverage the SB framework to propose an image-to-image translation pipeline for retinal image enhancement. Additionally, previous methods often fail to capture fine struc tural details, such as blood vessels. To address this, we enhance our pipeline by introducing Dynamic Snake Convolution, whose tortuous receptive field can better preserve tubular structures. We name the resulting retinal fundus image enhancement framework the Context-aware Unpaired Neural Schrödinger Bridge (CUNSB-RFIE). To the best of our knowledge, this is the first endeavor to use the SB approach for retinal image enhancement. Experimental results on a large-scale dataset demonstrate the advantage of the proposed method compared to several state-of-the-art supervised and unsupervised methods in terms of image quality and performance on downstream tasks.The code is available at https://github.com/Retinal-Research/CUNSB-RFIE.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"4502-4511"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12408487/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145016765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models. SODA：光谱正交分解自适应扩散模型。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00458

Xinxi Zhang, Song Wen, Ligong Han, Felix Juefei-Xu, Akash Srivastava, Junzhou Huang, Vladimir Pavlovic, Hao Wang, Molei Tao, Dimitris Metaxas

{"title":"SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models.","authors":"Xinxi Zhang, Song Wen, Ligong Han, Felix Juefei-Xu, Akash Srivastava, Junzhou Huang, Vladimir Pavlovic, Hao Wang, Molei Tao, Dimitris Metaxas","doi":"10.1109/wacv61041.2025.00458","DOIUrl":"10.1109/wacv61041.2025.00458","url":null,"abstract":"Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. Specifically, we introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"4665-4682"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12085162/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement. 情境感知视网膜眼底图像增强的最优传输学习。

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision Pub Date : 2025-02-01 Epub Date: 2025-04-08 DOI: 10.1109/wacv61041.2025.00395

Vamsi Krishna Vasa, Yujian Xiong, Peijie Qiu, Oana Dumitrascu, Wenhui Zhu, Yalin Wang

{"title":"Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement.","authors":"Vamsi Krishna Vasa, Yujian Xiong, Peijie Qiu, Oana Dumitrascu, Wenhui Zhu, Yalin Wang","doi":"10.1109/wacv61041.2025.00395","DOIUrl":"10.1109/wacv61041.2025.00395","url":null,"abstract":"Retinal fundus photography offers a non-invasive way to diagnose and monitor a variety of retinal diseases, but is prone to inherent quality glitches arising from systemic imperfections or operator/patient-related factors. However, high-quality retinal images are crucial for carrying out accurate diagnoses and automated analyses. The fundus image enhancement is typically formulated as a distribution alignment problem, by finding a one-to-one mapping between a low-quality image and its high-quality counterpart. This paper proposes a context-informed optimal transport (OT) learning framework for tackling unpaired fundus image enhancement. In contrast to standard generative image enhancement methods, which struggle with handling contextual information (e.g., over-tampered local structures and unwanted artifacts), the proposed context-aware OT learning paradigm better preserves local structures and minimizes unwanted artifacts. Leveraging deep contextual features, we derive the proposed context-aware OT using the earth mover's distance and show that the proposed context-OT has a solid theoretical guarantee. Experimental results on a large-scale dataset demonstrate the superiority of the proposed method over several state-of-the-art supervised and unsupervised methods in terms of signal-to-noise ratio, structural similarity index, as well as two downstream tasks. The code is available at https://github.com/Retinal-Research/Contextual-OT.","PeriodicalId":73325,"journal":{"name":"IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision","volume":"2025 ","pages":"4016-4025"},"PeriodicalIF":0.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12337797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144823347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0