arXiv subjects

Wentao Liu

Publications and source records attributed to Wentao Liu.

At least 91 records · Page 5Linked to original sources

arXiv2024

UDCR: Unsupervised Aortic DSA/CTA Rigid Registration Using Deep Reinforcement Learning and Overlap Degree Calculation

The rigid registration of aortic Digital Subtraction Angiography (DSA) and Computed Tomography Angiography (CTA) can provide 3D anatomical details of the vasculature for the interventional surgical treatment of conditions such as aortic dissection and aortic aneurysms, holding significant value for clinical research. However, the current methods for 2D/3D image registration are dependent on manual annotations or synthetic data, as well as the extraction of landmarks, which is not suitable for cross-modal registration of aortic DSA/CTA. In this paper, we propose an unsupervised method, UDCR, for aortic DSA/CTA rigid registration based on deep reinforcement learning. Leveraging the imaging principles and characteristics of DSA and CTA, we have constructed a cross-dimensional registration environment based on spatial transformations. Specifically, we propose an overlap degree calculation reward function that measures the intensity difference between the foreground and background, aimed at assessing the accuracy of registration between segmentation maps and DSA images. This method is highly flexible, allowing for the loading of pre-trained models to perform registration directly or to seek the optimal spatial transformation parameters through online learning. We manually annotated 61 pairs of aortic DSA/CTA for algorithm evaluation. The results indicate that the proposed UDCR achieved a Mean Absolute Error (MAE) of 2.85 mm in translation and 4.35° in rotation, showing significant potential for clinical applications.

eess.IV↗

arXiv2024

Lorentz violation induces isospectrality breaking in Einstein-Bumblebee gravity theory

In this paper, we investigate the quasinormal modes (QNMs) of a Lorentz-violating spacetime, factoring in a cosmological constant, within the framework of Einstein-Bumblebee gravity. Our findings reveal that the interaction of spacetime with an anisotropic bumblebee field imparts distinct contributions to the axial and polar sectors of the vector perturbations. This subsequently breaks the isospectrality typically observed in vector modes. Numerical evidence strongly indicates isospectral breaking in the vector modes of Einstein-Bumblebee black holes: a pronounced breakage in the real part of the frequencies, while the imaginary component seems less affected. This isospectral breaking indicates the existence of two different waveforms in the Ringdown phase of the black hole, which provides a potential signal of quantum gravity observable in current experiments.

gr-qc↗

arXiv2024

DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception

Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be satisfied especially for real-time motion synthesis in scanned point cloud scenes, if multiple dynamic objects exist, e.g., moving persons or vehicles. To handle this problem, we propose the first Dynamic Environment MOtion Synthesis framework (DEMOS) to predict future motion instantly according to the current scene, and use it to dynamically update the latent motion for final motion synthesis. Concretely, we propose a Spherical-BEV perception method to extract local scene features that are specifically designed for instant scene-aware motion prediction. Then, we design a time-variant motion blending to fuse the new predicted motions into the latent motion, and the final motion is derived from the updated latent motions, benefitting both from motion-prior and iterative methods. We unify the data format of two prevailing datasets, PROX and GTA-IM, and take them for motion synthesis evaluation in 3D scenes. We also assess the effectiveness of the proposed method in dynamic environments from GTA-IM and Semantic3D to check the responsiveness. The results show our method outperforms previous works significantly and has great performance in handling dynamic environments.

cs.CV↗

arXiv2024

The Quasinormal Modes and Isospectrality of Bardeen (Anti-) de Sitter Black Holes

Black holes (BHs) exhibiting coordinate singularities but lacking essential singularities throughout the entire spacetime are referred to as regular black holes (RBHs). The initial formulation of RBHs was presented by Bardeen, who considered the Einstein equation coupled with a nonlinear electromagnetic field. In this study, we investigate the gravitational perturbations, including the axial and polar sectors, of the Bardeen (Anti-) de Sitter black holes. We derive the master equations with source terms for both axial and polar perturbations, and subsequently compute the quasinormal modes (QNMs) through numerical methods. For the Bardeen de Sitter black hole, we employ the 6th-order WKB approach. The numerical results reveal that the isospectrality is broken in this case. Conversely, for Bardeen Anti-de Sitter black holes, the QNM frequencies are calculated by using the HH method.

gr-qc↗

arXiv2024

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

Open-vocabulary dense prediction tasks including object detection and image segmentation have been advanced by the success of Contrastive Language-Image Pre-training (CLIP). CLIP models, particularly those incorporating vision transformers (ViTs), have exhibited remarkable generalization ability in zero-shot image classification. However, when transferring the vision-language alignment of CLIP from global image representation to local region representation for the open-vocabulary dense prediction tasks, CLIP ViTs suffer from the domain shift from full images to local image regions. In this paper, we embark on an in-depth analysis of the region-language alignment in CLIP models, which is essential for downstream open-vocabulary dense prediction tasks. Subsequently, we propose an approach named CLIPSelf, which adapts the image-level recognition ability of CLIP ViT to local image regions without needing any region-text pairs. CLIPSelf empowers ViTs to distill itself by aligning a region representation extracted from its dense feature map with the image-level representation of the corresponding image crop. With the enhanced CLIP ViTs, we achieve new state-of-the-art performance on open-vocabulary object detection, semantic segmentation, and panoptic segmentation across various benchmarks. Models and code are released at https://github.com/wusize/CLIPSelf.

cs.CV↗

arXiv2024

An Automatic Cascaded Model for Hemorrhagic Stroke Segmentation and Hemorrhagic Volume Estimation

Hemorrhagic Stroke (HS) has a rapid onset and is a serious condition that poses a great health threat. Promptly and accurately delineating the bleeding region and estimating the volume of bleeding in Computer Tomography (CT) images can assist clinicians in treatment planning, leading to improved treatment outcomes for patients. In this paper, a cascaded 3D model is constructed based on UNet to perform a two-stage segmentation of the hemorrhage area in CT images from rough to fine, and the hemorrhage volume is automatically calculated from the segmented area. On a dataset with 341 cases of hemorrhagic stroke CT scans, the proposed model provides high-quality segmentation outcome with higher accuracy (DSC 85.66%) and better computation efficiency (6.2 second per sample) when compared to the traditional Tada formula with respect to hemorrhage volume estimation.

eess.IV↗

arXiv2023

CLIM: Contrastive Language-Image Mosaic for Region Representation

Detecting objects accurately from a large or open vocabulary necessitates the vision-language alignment on region representations. However, learning such a region-text alignment by obtaining high-quality box annotations with text labels or descriptions is expensive and infeasible. In contrast, collecting image-text pairs is simpler but lacks precise object location information to associate regions with texts. In this paper, we propose a novel approach called Contrastive Language-Image Mosaic (CLIM), which leverages large-scale image-text pairs effectively for aligning region and text representations. CLIM combines multiple images into a mosaicked image and treats each image as a `pseudo region'. The feature of each pseudo region is extracted and trained to be similar to the corresponding text embedding while dissimilar from others by a contrastive loss, enabling the model to learn the region-text alignment without costly box annotations. As a generally applicable approach, CLIM consistently improves different open-vocabulary object detection methods that use caption supervision. Furthermore, CLIM can effectively enhance the region representation of vision-language models, thus providing stronger backbones for open-vocabulary object detectors. Our experimental results demonstrate that CLIM improves different baseline open-vocabulary object detectors by a large margin on both OV-COCO and OV-LVIS benchmarks. The code is available at https://github.com/wusize/CLIM.

cs.CV↗

arXiv2023

Two-Stage Hybrid Supervision Framework for Fast, Low-resource, and Accurate Organ and Pan-cancer Segmentation in Abdomen CT

Abdominal organ and tumour segmentation has many important clinical applications, such as organ quantification, surgical planning, and disease diagnosis. However, manual assessment is inherently subjective with considerable inter- and intra-expert variability. In the paper, we propose a hybrid supervised framework, StMt, that integrates self-training and mean teacher for the segmentation of abdominal organs and tumors using partially labeled and unlabeled data. We introduce a two-stage segmentation pipeline and whole-volume-based input strategy to maximize segmentation accuracy while meeting the requirements of inference time and GPU memory usage. Experiments on the validation set of FLARE2023 demonstrate that our method achieves excellent segmentation performance as well as fast and low-resource model inference. Our method achieved an average DSC score of 89.79\% and 45.55 \% for the organs and lesions on the validation set and the average running time and area under GPU memory-time cure are 11.25s and 9627.82MB, respectively.

eess.IV↗

arXiv2023

Gravito-electromagnetic perturbations of MOG black holes with a cosmological constant: Quasinormal modes and Ringdown waveforms

In this paper, we present a black hole solution with a cosmological constant in the Scalar-Tensor-Vector Modified Gravity (MOG) theory, where the strength of the gravitational constant is determined by $G = G_\text{N}(1+α)$. We derive the master equations for gravito-electromagnetic perturbations and numerically solve for the Quasinormal Mode (QNM) spectrum and the ringdown waveforms. Our research results show that increasing the MOG parameter $α$ leads to a decrease in both the real and imaginary parts of the QNM frequencies for electromagnetic and gravitational modes. Similarly, increasing the cosmological constant $Λ$ also results in a decrease in both the real and imaginary parts of the QNM frequencies for these modes. These trends are observed when compared to standard Schwarzschild-de Sitter (S-dS) or MOG black holes, respectively. Meanwhile, the result indicates that in the MOG-de Sitter spacetime, the frequencies for electromagnetic and gravitational modes display isospectrality, and exhibit the same ringdown waveforms. Our findings have implications for the ringdown phase of mergers involving massive compact objects, which is of particular relevance given the recent detections of gravitational waves by LIGO.

gr-qc↗

arXiv2023

Automatic Animation of Hair Blowing in Still Portrait Photos

We propose a novel approach to animate human hair in a still portrait photo. Existing work has largely studied the animation of fluid elements such as water and fire. However, hair animation for a real image remains underexplored, which is a challenging problem, due to the high complexity of hair structure and dynamics. Considering the complexity of hair structure, we innovatively treat hair wisp extraction as an instance segmentation problem, where a hair wisp is referred to as an instance. With advanced instance segmentation networks, our method extracts meaningful and natural hair wisps. Furthermore, we propose a wisp-aware animation module that animates hair wisps with pleasing motions without noticeable artifacts. The extensive experiments show the superiority of our method. Our method provides the most pleasing and compelling viewing experience in the qualitative experiments and outperforms state-of-the-art still-image animation methods by a large margin in the quantitative evaluation. Project url: \url{https://nevergiveu.github.io/AutomaticHairBlowing/}

cs.CV↗

arXiv2023

TSI-Net: A Timing Sequence Image Segmentation Network for Intracranial Artery Segmentation in Digital Subtraction Angiography

Cerebrovascular disease is one of the major diseases facing the world today. Automatic segmentation of intracranial artery (IA) in digital subtraction angiography (DSA) sequences is an important step in the diagnosis of vascular related diseases and in guiding neurointerventional procedures. While, a single image can only show part of the IA within the contrast medium according to the imaging principle of DSA technology. Therefore, 2D DSA segmentation methods are unable to capture the complete IA information and treatment of cerebrovascular diseases. We propose A timing sequence image segmentation network with U-shape, called TSI-Net, which incorporates a bi-directional ConvGRU module (BCM) in the encoder. The network incorporates a bi-directional ConvGRU module (BCM) in the encoder, which can input variable-length DSA sequences, retain past and future information, segment them into 2D images. In addition, we introduce a sensitive detail branch (SDB) at the end for supervising fine vessels. Experimented on the DSA sequence dataset DIAS, the method performs significantly better than state-of-the-art networks in recent years. In particular, it achieves a Sen evaluation metric of 0.797, which is a 3% improvement compared to other methods.

eess.IV↗

arXiv2023

Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge

Quantitative organ assessment is an essential step in automated abdominal disease diagnosis and treatment planning. Artificial intelligence (AI) has shown great potential to automatize this process. However, most existing AI algorithms rely on many expert annotations and lack a comprehensive evaluation of accuracy and efficiency in real-world multinational settings. To overcome these limitations, we organized the FLARE 2022 Challenge, the largest abdominal organ analysis challenge to date, to benchmark fast, low-resource, accurate, annotation-efficient, and generalized AI algorithms. We constructed an intercontinental and multinational dataset from more than 50 medical groups, including Computed Tomography (CT) scans with different races, diseases, phases, and manufacturers. We independently validated that a set of AI algorithms achieved a median Dice Similarity Coefficient (DSC) of 90.0\% by using 50 labeled scans and 2000 unlabeled scans, which can significantly reduce annotation requirements. The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89.5\%, 90.9\%, and 88.3\% on North American, European, and Asian cohorts, respectively. They also enabled automatic extraction of key organ biology features, which was labor-intensive with traditional manual measurements. This opens the potential to use unlabeled data to boost performance and alleviate annotation shortages for modern AI models.

eess.IV↗

arXiv2023

Aligning Bag of Regions for Open-Vocabulary Object Detection

Pre-trained vision-language models (VLMs) learn to align vision and language representations on large-scale datasets, where each image-text pair usually contains a bag of semantic concepts. However, existing open-vocabulary object detectors only align region embeddings individually with the corresponding features extracted from the VLMs. Such a design leaves the compositional structure of semantic concepts in a scene under-exploited, although the structure may be implicitly learned by the VLMs. In this work, we propose to align the embedding of bag of regions beyond individual regions. The proposed method groups contextually interrelated regions as a bag. The embeddings of regions in a bag are treated as embeddings of words in a sentence, and they are sent to the text encoder of a VLM to obtain the bag-of-regions embedding, which is learned to be aligned to the corresponding features extracted by a frozen VLM. Applied to the commonly used Faster R-CNN, our approach surpasses the previous best results by 4.6 box AP50 and 2.8 mask AP on novel categories of open-vocabulary COCO and LVIS benchmarks, respectively. Code and models are available at https://github.com/wusize/ovdet.

cs.CV↗

arXiv2023

QNMs of slowly rotating Einstein-Bumblebee Black Hole

We have studied the quasinormal modes (QNMs) of a slowly rotating black hole with Lorentz-violating parameter in Einstein-bumblebee gravity. We analyse the slow rotation approximation of the rotating black hole in the Einstein-bumblebee gravity, and obtain the master equations for scalar perturbation, vector perturbation and axial gravitational perturbation, respectively. Using the matrix method and the continuous fraction method, we numerically calculate the QNM frequencies. In particular, for scalar field, it shows that the QNMs up to the second order of rotation parameter have higher accuracy. The numerical results show that, for both scalar and vector fields, the Lorentz-violating parameter has a significant effect on the imaginary part of the QNM frequencies, while having a relatively smaller impact on the real part of the QNM frequencies. But for axial gravitational perturbation, the effect of increasing the Lorentz-violating parameter $\ell$ is similar to that of increasing the rotation parameter $\tilde{a}$.

gr-qc↗

arXiv2022

Transforming the Interactive Segmentation for Medical Imaging

The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example, on segmenting cancer or small organs. Specifically, we propose a novel Transformer-based architecture for Interactive Segmentation (TIS), that treats the refinement task as a procedure for grouping pixels with similar features to those clicks given by the end users. Our proposed architecture is composed of Transformer Decoder variants, which naturally fulfills feature comparison with the attention mechanisms. In contrast to existing approaches, our proposed TIS is not limited to binary segmentations, and allows the user to edit masks for arbitrary number of categories. To validate the proposed approach, we conduct extensive experiments on three challenging datasets and demonstrate superior performance over the existing state-of-the-art methods. The project page is: https://wtliu7.github.io/tis/.

cs.CV↗

arXiv2022

Gauge Invariant Perturbations of General Spherically Symmetric Spacetimes

In this paper, the gauge choices in general spherically symmetric spacetimes have been explored. We construct the gauge invariant variables and the master equations for both the Detweiler easy gauge and the Regge-Wheeler gauge, respectively. The particular cases for $l=0,1$ are also been investigated. Our results provide analytical calculations of metric perturbation in general spherically symmetric spacetimes, which can be applied to various cases, including the Effective-One-Body problem. A simple example is presented to show how the metric perturbation components are related to the source perturbation terms.

gr-qc↗

arXiv2022

Combining Self-Training and Hybrid Architecture for Semi-supervised Abdominal Organ Segmentation

Abdominal organ segmentation has many important clinical applications, such as organ quantification, surgical planning, and disease diagnosis. However, manually annotating organs from CT scans is time-consuming and labor-intensive. Semi-supervised learning has shown the potential to alleviate this challenge by learning from a large set of unlabeled images and limited labeled samples. In this work, we follow the self-training strategy and employ a high-performance hybrid architecture (PHTrans) consisting of CNN and Swin Transformer for the teacher model to generate precise pseudo labels for unlabeled data. Afterward, we introduce them with labeled data together into a two-stage segmentation framework with lightweight PHTrans for training to improve the performance and generalization ability of the model while remaining efficient. Experiments on the validation set of FLARE2022 demonstrate that our method achieves excellent segmentation performance as well as fast and low-resource model inference. The average DSC and NSD are 0.8956 and 0.9316, respectively. Under our development environments, the average inference time is 18.62 s, the average maximum GPU memory is 1995.04 MB, and the area under the GPU memory-time curve and the average area under the CPU utilization-time curve are 23196.84 and 319.67. The code is available at https://github.com/lseventeen/FLARE22-TwoStagePHTrans.

cs.CV↗

arXiv2022

ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild

This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.

cs.CV↗