arXiv subjects

Shenghua Gao

Publications and source records attributed to Shenghua Gao.

At least 91 records · Page 5Linked to original sources

arXiv2020

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

We tackle human image synthesis, including human motion imitation, appearance transfer, and novel view synthesis, within a unified framework. It means that the model, once being trained, can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints to estimate the human body structure. However, they only express the position information with no abilities to characterize the personalized shape of the person and model the limb rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape. It can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose an Attentional Liquid Warping GAN with Attentional Liquid Warping Block (AttLWB) that propagates the source information in both image and feature spaces to the synthesized reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method can support a more flexible warping from multiple sources. To further improve the generalization ability of the unseen source images, a one/few-shot adversarial learning is applied. In detail, it firstly trains a model in an extensive training set. Then, it finetunes the model by one/few-shot unseen image(s) in a self-supervised way to generate high-resolution (512 x 512 and 1024 x 1024) results. Also, we build a new dataset, namely iPER dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our methods in terms of preserving face identity, shape consistency, and clothes details. All codes and dataset are available on https://impersonator.org/work/impersonator-plus-plus.html.

cs.CV↗

arXiv2020

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions. Explicitly characterizing an object-level relationship while distilling spatial relationships are currently absent but crucial to this task. Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network. Specifically, visual features are firstly correlated at an implicit object-level in a projected latent space; then they are distilled by each spatial relationship word, resulting in each differently activated feature representing each spatial relationship. Further, we introduce global position priors to fix the absence of positional information, which may result in global positional reasoning ambiguities. Both the linguistic and visual features are concatenated to finalize the target localization. Experimental results on the Touchdown show that our method is around 24\% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.

cs.CV↗

arXiv2020

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions, by only leveraging normal images in training phase. Normal images from healthy subjects often have regular structures (e.g., the structured blood vessels in the fundus image, or structured anatomy in optical coherence tomography image). On the contrary, the diseases and lesions often destroy these structures. Motivated by this, we propose to leverage the relation between the image texture and structure to design a deep neural network for anomaly detection. Specifically, we first extract the structure of the retinal images, then we combine both the structure features and the last layer features extracted from original health image to reconstruct the original input healthy image. The image feature provides the texture information and guarantees the uniqueness of the image recovered from the structure. In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image. On the one hand, minimizing the reconstruction difference behaves like a regularizer to guarantee that the image is corrected reconstructed. On the other hand, such structure difference can also be used as a metric for normality measurement. The whole network is termed as P-Net because it has a ``P'' shape. Extensive experiments on RESC dataset and iSee dataset validate the effectiveness of our approach for anomaly detection in retinal images. Further, our method also generalizes well to novel class discovery in retinal images and anomaly detection in real-world images.

eess.IV↗

arXiv2020

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Recently, there has been growing interest in developing learning-based methods to detect and utilize salient semi-global or global structures, such as junctions, lines, planes, cuboids, smooth surfaces, and all types of symmetries, for 3D scene modeling and understanding. However, the ground truth annotations are often obtained via human labor, which is particularly challenging and inefficient for such tasks due to the large number of 3D structure instances (e.g., line segments) and other factors such as viewpoints and occlusions. In this paper, we present a new synthetic dataset, Structured3D, with the aim of providing large-scale photo-realistic images with rich 3D structure annotations for a wide spectrum of structured 3D modeling tasks. We take advantage of the availability of professional interior designs and automatically extract 3D structures from them. We generate high-quality images with an industry-leading rendering engine. We use our synthetic dataset in combination with real images to train deep networks for room layout estimation and demonstrate improved performance on benchmark datasets.

cs.CV↗

arXiv2020

Learning to Parse Wireframes in Images of Man-Made Environments

In this paper, we propose a learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe.

cs.CV↗

arXiv2020

P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

This paper tackles the unsupervised depth estimation task in indoor environments. The task is extremely challenging because of the vast areas of non-texture regions in these scenes. These areas could overwhelm the optimization process in the commonly used unsupervised depth estimation framework proposed for outdoor environments. However, even when those regions are masked out, the performance is still unsatisfactory. In this paper, we argue that the poor performance suffers from the non-discriminative point-based matching. To this end, we propose P$^2$Net. We first extract points with large local gradients and adopt patches centered at each point as its representation. Multiview consistency loss is then defined over patches. This operation significantly improves the robustness of the network training. Furthermore, because those textureless regions in indoor scenes (e.g., wall, floor, roof, \etc) usually correspond to planar regions, we propose to leverage superpixels as a plane prior. We enforce the predicted depth to be well fitted by a plane within each superpixel. Extensive experiments on NYUv2 and ScanNet show that our P$^2$Net outperforms existing approaches by a large margin. Code is available at \url{https://github.com/svip-lab/Indoor-SfMLearner}.

cs.CV↗

arXiv2020

Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement

Almost all previous deep learning-based multi-view stereo (MVS) approaches focus on improving reconstruction quality. Besides quality, efficiency is also a desirable feature for MVS in real scenarios. Towards this end, this paper presents a Fast-MVSNet, a novel sparse-to-dense coarse-to-fine framework, for fast and accurate depth estimation in MVS. Specifically, in our Fast-MVSNet, we first construct a sparse cost volume for learning a sparse and high-resolution depth map. Then we leverage a small-scale convolutional neural network to encode the depth dependencies for pixels within a local region to densify the sparse high-resolution depth map. At last, a simple but efficient Gauss-Newton layer is proposed to further optimize the depth map. On one hand, the high-resolution depth map, the data-adaptive propagation method and the Gauss-Newton layer jointly guarantee the effectiveness of our method. On the other hand, all modules in our Fast-MVSNet are lightweight and thus guarantee the efficiency of our approach. Besides, our approach is also memory-friendly because of the sparse depth representation. Extensive experimental results show that our method is 5$\times$ and 14$\times$ faster than Point-MVSNet and R-MVSNet, respectively, while achieving comparable or even better results on the challenging Tanks and Temples dataset as well as the DTU dataset. Code is available at https://github.com/svip-lab/FastMVSNet.

cs.CV↗

arXiv2020

High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning

Reducing the bit-depth is an effective approach to lower the cost of optical coherence tomography (OCT) systems and increase the transmission efficiency in data acquisition and telemedicine. However, a low bit-depth will lead to the degeneration of the detection sensitivity thus reduce the signal-to-noise ratio (SNR) of OCT images. In this paper, we propose to use deep learning for the reconstruction of the high SNR OCT images from the low bit-depth acquisition. Its feasibility was preliminarily evaluated by applying the proposed method to the quantized $3\sim8$-bit data from native 12-bit interference fringes. We employed a pixel-to-pixel generative adversarial network architecture in the low to high bit-depth OCT image transition. Retinal OCT data of a healthy subject from a homemade spectral-domain OCT system was used in the study. Extensively qualitative and quantitative results show this deep-learning-based approach could significantly improve the SNR of the low bit-depth OCT images especially at the choroidal region. Superior similarity and SNR between the reconstructed images and the original 12-bit OCT images could be derived when the bit-depth $\geq 5$. This work demonstrates the proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings.

eess.IV↗

arXiv2020

Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image

With the development of convolutional neural network, deep learning has shown its success for retinal disease detection from optical coherence tomography (OCT) images. However, deep learning often relies on large scale labelled data for training, which is oftentimes challenging especially for disease with low occurrence. Moreover, a deep learning system trained from data-set with one or a few diseases is unable to detect other unseen diseases, which limits the practical usage of the system in disease screening. To address the limitation, we propose a novel anomaly detection framework termed Sparsity-constrained Generative Adversarial Network (Sparse-GAN) for disease screening where only healthy data are available in the training set. The contributions of Sparse-GAN are two-folds: 1) The proposed Sparse-GAN predicts the anomalies in latent space rather than image-level; 2) Sparse-GAN is constrained by a novel Sparsity Regularization Net. Furthermore, in light of the role of lesions for disease screening, we present to leverage on an anomaly activation map to show the heatmap of lesions. We evaluate our proposed Sparse-GAN on a publicly available dataset, and the results show that the proposed method outperforms the state-of-the-art methods.

cs.CV↗

arXiv2020

Digital resolution enhancement in low transverse sampling optical coherence tomography angiography using deep learning

Optical coherence tomography angiography (OCTA) requires high transverse sampling density for visualizing retinal and choroidal capillaries. Low transverse sampling causes resolution degradation, such as the angiograms in wide-field OCTA. In this paper, we propose to address this problem using deep learning. We conducted extensive experiments on converting the centrally cropped 3 x 3 mm2 field of view (FOV) of the 8 x 8 mm2 foveal OCTA images (a sampling density of 22.9 $μ$m) to the native 3 x 3 mm2 en face OCTA images (a sampling density of 12.2 $μ$m). We employed a cycle-consistent adversarial network architecture in this conversion. The quantitative analysis using the perceptual similarity measures shows the generated OCTA images are closer to the native 3 x 3 mm2 scans. Besides, the results show the proposed method could also enhance signal-to-noise ratio. We further applied our method to enhance diseased cases and calculate vascular biomarkers, which demonstrates its generalization performance and clinical perspective.

eess.IV↗

arXiv2019

BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images

Choroid is the vascular layer of the eye, which is directly related to the incidence and severity of many ocular diseases. Optical Coherence Tomography (OCT) is capable of imaging both the cross-sectional view of retina and choroid, but the segmentation of the choroid region is challenging because of the fuzzy choroid-sclera interface (CSI). In this paper, we propose a biomarker infused global-to-local network (BioNet) for choroid segmentation, which segments the choroid with higher credibility and robustness. Firstly, our method trains a biomarker prediction network to learn the features of the biomarker. Then a global multi-layers segmentation module is applied to segment the OCT image into 12 layers. Finally, the global multi-layered result and the original OCT image are fed into a local choroid segmentation module to segment the choroid region with the biomarker infused as regularizer. We conducted comparison experiments with the state-of-the-art methods on a dataset (named AROD). The experimental results demonstrate the superiority of our method with $90.77\%$ Dice-index and 6.23 pixels Average-unsigned-surface-detection-error, etc.

cs.CV↗

arXiv2019

Perceptual-assisted Adversarial Adaptation for Choroid Segmentation in optical coherence tomography

Accurate choroid segmentation in optical coherence tomography (OCT) image is vital because the choroid thickness is a major quantitative biomarker of many ocular diseases. Deep learning has shown its superiority in the segmentation of the choroid region but subjects to the performance degeneration caused by the domain discrepancies (e.g., noise level and distribution) among datasets obtained from the OCT devices of different manufacturers. In this paper, we present an unsupervised perceptual-assisted adversarial adaptation (PAAA) framework for efficiently segmenting the choroid area by narrowing the domain discrepancies between different domains. The adversarial adaptation module in the proposed framework encourages the prediction structure information of the target domain to be similar to that of the source domain. Besides, a perceptual loss is employed for matching their shape information (the curvatures of Bruch's membrane and choroid-sclera interface) which can result in a fine boundary prediction. The results of quantitative experiments show that the proposed PAAA segmentation framework outperforms other state-of-the-art methods.

eess.IV↗

arXiv2019

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Purpose: To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists and the training datasets for the classification of various retinal disorders using deep learning (DL). Methods: The GANs architecture was adopted to synthesis high-resolution OCT images training on a publicly available OCT dataset including urgent referrals (choroidal neovascularization and diabetic macular edema) and non-urgent referrals (normal and drusen). 400 real and synthetic OCT images were evaluated by 2 retinal specialists to assess image quality. We further trained 2 DL models on either real or synthetic datasets and compared the performance of urgent vs nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital). Results: The image quality of real vs synthetic OCT images was similar as assessed by 2 retinal specialists. The accuracy of discrimination as real vs synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98 respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R, 0.90 for DL_Model_S. Conclusions: The GAN-synthetic OCT images can be used by clinicians for educational purposes and developing DL algorithms. Translational Relevance: The medical image synthesis based on GANs is promising in human and machine to fulfill clinical tasks.

physics.med-ph↗

arXiv2019

Eliminating Shadow Artifacts via Generative Inpainting Networks to Quantify Vascular Changes of the Choroid

Shadow artifacts from retinal vessels hinder the development of quantitative choroidal biomarkers in Optical Coherence Tomography (OCT), which limits the clinical applications of the choroidal OCT to the measures of layer thickness. In this paper, we present a novel framework that could eliminate the retinal shadows and realize the quantification of choroidal vasculature. Different from existing methods, we convert the shadow elimination into an object removal task, which can be handled by image inpainting techniques. We adopt and finetune a two-stage generative inpainting network which connects the edges of the vessels ahead of refilling the shadow-contaminated areas. It shows surpassing performance in repairing the choroidal vasculature compared with traditional inpainting algorithms. We further verify the feasibility of the proposed frame using a prospective observational study, which detects the choroidal vascular changes related to the Intra-Ocular Pressure (IOP) elevation of 34 healthy volunteers. As the average IOP increases from $15.84\pm1.99$ mmHg to $34.48\pm5.35$ mmHg, we achieve the decreases of the choroidal vessel density and flow index from $0.491\pm0.020$ to $0.463\pm0.019$ and from $0.336\pm0.025$ to $0.300\pm0.019$, respectively.

physics.med-ph↗

arXiv2019

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only expresses the position information with no abilities to characterize the personalized shape of the individual person and model the limbs rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose a Liquid Warping GAN with Liquid Warping Block (LWB) that propagates the source information in both image and feature spaces, and synthesizes an image with respect to the reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method is able to support a more flexible warping from multiple sources. In addition, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our method in several aspects, such as robustness in occlusion case and preserving face identity, shape consistency and clothes details. All codes and datasets are available on https://svip-lab.github.io/project/impersonator.html

cs.CV↗

arXiv2019

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps. The sem-dist map is a kind of level-set representation, of which the different regions of an object are placed into different levels on the map according to their visibility. It is a natural extension of masks and heatmaps, where modal, amodal segmentation, as well as depth order information, are all well-described. Then we also introduce a novel convolutional neural network (CNN) architecture, which we refer to as semantic layering network, to estimate sem-dist maps layer by layer, from the global-level to the instance-level, for all objects in an image. Extensive experiments on the COCOA and D2SA datasets have demonstrated that our framework can predict amodal segmentation, occlusion and depth order with state-of-the-art performance.

cs.CV↗

arXiv2019

SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis

Generative Adversarial Networks (GANs) have the capability of synthesizing images, which have been successfully applied to medical image synthesis tasks. However, most of existing methods merely consider the global contextual information and ignore the fine foreground structures, e.g., vessel, skeleton, which may contain diagnostic indicators for medical image analysis. Inspired by human painting procedure, which is composed of stroking and color rendering steps, we propose a Sketching-rendering Unconditional Generative Adversarial Network (SkrGAN) to introduce a sketch prior constraint to guide the medical image generation. In our SkrGAN, a sketch guidance module is utilized to generate a high quality structural sketch from random noise, then a color render mapping is used to embed the sketch-based representations and resemble the background appearances. Experimental results show that the proposed SkrGAN achieves the state-of-the-art results in synthesizing images for various image modalities, including retinal color fundus, X-Ray, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). In addition, we also show that the performances of medical image segmentation method have been improved by using our synthesized images as data augmentation.

cs.CV↗

arXiv2019

Locality-constrained Spatial Transformer Network for Video Crowd Counting

Compared with single image based crowd counting, video provides the spatial-temporal information of the crowd that would help improve the robustness of crowd counting. But translation, rotation and scaling of people lead to the change of density map of heads between neighbouring frames. Meanwhile, people walking in/out or being occluded in dynamic scenes leads to the change of head counts. To alleviate these issues in video crowd counting, a Locality-constrained Spatial Transformer Network (LSTN) is proposed. Specifically, we first leverage a Convolutional Neural Networks to estimate the density map for each frame. Then to relate the density maps between neighbouring frames, a Locality-constrained Spatial Transformer (LST) module is introduced to estimate the density map of next frame with that of current frame. To facilitate the performance evaluation, a large-scale video crowd counting dataset is collected, which contains 15K frames with about 394K annotated heads captured from 13 different scenes. As far as we know, it is the largest video crowd counting dataset. Extensive experiments on our dataset and other crowd counting datasets validate the effectiveness of our LSTN for crowd counting.

cs.CV↗