Image-guided depth completion aims at generating a dense depth map from sparse LiDAR data and RGB image. Recent methods have shown promising performance by reformulating it as a classification problem with two sub-tasks: depth discretization and probability prediction. They divide the depth range into several discrete depth values as depth categories, serving as priors for scene depth distributions. However, previous depth discretization methods are easy to be impacted by depth distribution variations across different scenes, resulting in suboptimal scene depth distribution priors. To address the above problem, we propose a progressive depth decoupling and modulating network, which incrementally decouples the depth range into bins and adaptively generates multi-scale dense depth maps in multiple stages. Specifically, we first design a Bins Initializing Module (BIM) to construct the seed bins by exploring the depth distribution information within a sparse depth map, adapting variations of depth distribution. Then, we devise an incremental depth decoupling branch to progressively refine the depth distribution information from global to local. Meanwhile, an adaptive depth modulating branch is developed to progressively improve the probability representation from coarse-grained to fine-grained. And the bi-directional information interactions are proposed to strengthen the information interaction between those two branches (sub-tasks) for promoting information complementation in each branch. Further, we introduce a multi-scale supervision mechanism to learn the depth distribution information in latent features and enhance the adaptation capability across different scenes. Experimental results on public datasets demonstrate that our method outperforms the state-of-the-art methods. The code will be open-sourced at [this https URL](https://github.com/Cisse-away/PDDM).
Depth images and thermal images contain the spatial geometry information and surface temperature information, which can act as complementary information for the RGB modality. However, the quality of the depth and thermal images is often unreliable in some challenging scenarios, which will result in the performance degradation of the two-modal based salient object detection (SOD). Meanwhile, some researchers pay attention to the triple-modal SOD task, where they attempt to explore the complementarity of the RGB image, the depth image, and the thermal image. However, existing triple-modal SOD methods fail to perceive the quality of depth maps and thermal images, which leads to performance degradation when dealing with scenes with low-quality depth and thermal images. Therefore, we propose a quality-aware selective fusion network (QSF-Net) to conduct VDT salient object detection, which contains three subnets including the initial feature extraction subnet, the quality-aware region selection subnet, and the region-guided selective fusion subnet. Firstly, except for extracting features, the initial feature extraction subnet can generate a preliminary prediction map from each modality via a shrinkage pyramid architecture. Then, we design the weakly-supervised quality-aware region selection subnet to generate the quality-aware maps. Concretely, we first find the high-quality and low-quality regions by using the preliminary predictions, which further constitute the pseudo label that can be used to train this subnet. Finally, the region-guided selective fusion subnet purifies the initial features under the guidance of the quality-aware maps, and then fuses the triple-modal features and refines the edge details of prediction maps through the intra-modality and inter-modality attention (IIA) module and the edge refinement (ER) module, respectively. Extensive experiments are performed on VDT-2048
Cell segmentation is essential in biomedical research for analyzing cellular morphology and behavior. Deep learning methods, particularly convolutional neural networks (CNNs), have revolutionized cell segmentation by extracting intricate features from images. However, the robustness of these methods under microscope optical aberrations remains a critical challenge. This study comprehensively evaluates the performance of cell instance segmentation models under simulated aberration conditions using the DynamicNuclearNet (DNN) and LIVECell datasets. Aberrations, including Astigmatism, Coma, Spherical, and Trefoil, were simulated using Zernike polynomial equations. Various segmentation models, such as Mask R-CNN with different network heads (FPN, C3) and backbones (ResNet, VGG19, SwinS), were trained and tested under aberrated conditions. Results indicate that FPN combined with SwinS demonstrates superior robustness in handling simple cell images affected by minor aberrations. Conversely, Cellpose2.0 proves effective for complex cell images under similar conditions. Our findings provide insights into selecting appropriate segmentation models based on cell morphology and aberration severity, enhancing the reliability of cell segmentation in biomedical applications. Further research is warranted to validate these methods with diverse aberration types and emerging segmentation models. Overall, this research aims to guide researchers in effectively utilizing cell segmentation models in the presence of minor optical aberrations.
Cross-view geo-localization aims to match images of the same target from different platforms, e.g., drone and satellite. It is a challenging task due to the changing both appearance of targets and environmental content from different views. Existing methods mainly focus on digging more comprehensive information through feature maps segmentation, while inevitably destroy the image structure and are sensitive to the shifting and scale of the target in the query. To address the above issues, we introduce a simple yet effective part-based representation learning, called shifting-dense partition learning (SDPL). Specifically, we propose the dense partition strategy (DPS), which divides the image into multiple parts to explore contextual-information while explicitly maintain the global structure. To handle scenarios with non-centered targets, we further propose the shifting-fusion strategy, which generates multiple sets of parts in parallel based on various segmentation centers and then adaptively fuses all features to select the best partitions. Extensive experiments show that our SDPL is robust to position shifting and scale variations, and achieves competitive performance on two prevailing benchmarks, i.e., University-1652 and SUES-200.
Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model.
Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync. Extensive experiments on two of the primary benchmarks, V2C and Grid, demonstrate the favorable performance of the proposed method as compared to the current state-of-the-art. The source code and trained models will be released to the public.
As the size of the datasets getting larger, accurately annotating such datasets is becoming more impractical due to the expensiveness on both time and economy. Therefore, crowd-sourcing has been widely adopted to alleviate the cost of collecting labels, which also inevitably introduces label noise and eventually degrades the performance of the model. To learn from crowd-sourcing annotations, modeling the expertise of each annotator is a common but challenging paradigm, because the annotations collected by crowd-sourcing are usually highly-sparse. To alleviate this problem, we propose Coupled Confusion Correction (CCC), where two models are simultaneously trained to correct the confusion matrices learned by each other. Via bi-level optimization, the confusion matrices learned by one model can be corrected by the distilled data from the other. Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together. In this way, the expertise of the annotators, especially of those who provide seldom labels, could be better captured. Remarkably, we point out that the annotation sparsity not only means the average number of labels is low, but also there are always some annotators who provide very few labels, which is neglected by previous works when constructing synthetic crowd-sourcing annotations. Based on that, we propose to use Beta distribution to control the generation of the crowd-sourcing labels so that the synthetic annotations could be more consistent with the real-world ones. Extensive experiments are conducted on two types of synthetic datasets and three real-world datasets, the results of which demonstrate that CCC significantly outperforms state-of-the-art approaches.
The spatial and quantitative parameters of macular holes are vital for diagnosis, surgical choices, and post-op monitoring. Macular hole diagnosis and treatment rely heavily on spatial and quantitative data, yet the scarcity of such data has impeded the progress of deep learning techniques for effective segmentation and real-time 3D reconstruction. To address this challenge, we assembled the world's largest macular hole dataset, Retinal OCTfor Macular Hole Enhancement (ROME-3914), and a Comprehensive Archive for Retinal Segmentation (CARS-30k), both expertly annotated. In addition, we developed an innovative 3D segmentation network, the Dual-Encoder FuGH Network (DEFN), which integrates three innovative modules: Fourier Group Harmonics (FuGH), Simplified 3D Spatial Attention (S3DSA) and Harmonic Squeeze-and-Excitation Module (HSE). These three modules synergistically filter noise, reduce computational complexity, emphasize detailed features, and enhance the network's representation ability. We also proposed a novel data augmentation method, Stochastic Retinal Defect Injection (SRDI), and a network optimization strategy DynamicWeightCompose (DWC), to further improve the performance of DEFN. Compared with 13 baselines, our DEFN shows the best performance. We also offer precise 3D retinal reconstruction and quantitative metrics, bringing revolutionary diagnostic and therapeutic decision-making tools for ophthalmologists, and is expected to completely reshape the diagnosis and treatment patterns of difficult-to-treat macular degeneration. The source code is publicly available at: https://github.com/IIPL-HangzhouDianUniversity/DEFN-Pytorch.
Light-field fluorescence microscopy (LFM) is a powerful elegant compact method for long-term high-speed imaging of complex biological systems, such as neuron activities and rapid movements of organelles. LFM experiments typically generate terabytes image data and require a huge number of storage space. Some lossy compression algorithms have been proposed recently with good compression performance. However, since the specimen usually only tolerates low power density illumination for long-term imaging with low phototoxicity, the image signal-to-noise ratio (SNR) is relative-ly low, which will cause the loss of some efficient position or intensity information by using such lossy compression al-gorithms. Here, we propose a phase-space continuity enhanced bzip2 (PC-bzip2) lossless compression method for LFM data as a high efficiency and open-source tool, which combines GPU-based fast entropy judgement and multi-core-CPU-based high-speed lossless compression. Our proposed method achieves almost 10% compression ratio improvement while keeping the capability of high-speed compression, compared with original bzip2. We evaluated our method on fluorescence beads data and fluorescence staining cells data with different SNRs. Moreover, by introducing the temporal continuity, our method shows the superior compression ratio on time series data of zebrafish blood vessels.
Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by proposing a self-supervised cross-view representation reconstruction (SCORER) network. Concretely, we first design a multi-head token-wise matching to model relationships between cross-view features from similar/dissimilar images. Then, by maximizing cross-view contrastive alignment of two similar images, SCORER learns two view-invariant image representations in a self-supervised way. Based on these, we reconstruct the representations of unchanged objects by cross-attention, thus learning a stable difference representation for caption generation. Further, we devise a cross-modal backward reasoning to improve the quality of caption. This module reversely models a ``hallucination'' representation with the caption and ``before'' representation. By pushing it closer to the ``after'' representation, we enforce the caption to be informative about the difference in a self-supervised manner. Extensive experiments show our method achieves the state-of-the-art results on four datasets. The code is available at https://github.com/tuyunbin/SCORER.