In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data. Our main idea is bridging the photo domain $\mathcal{X}$ and the sketch domain $Y$ by using the line-drawing domain $\mathcal{Z}$. Specially, we map both photos and sketches to line-drawings by using a neural style transfer method, i.e. $F: \mathcal{X}/\mathcal{Y} \mapsto \mathcal{Z}$. Consequently, we obtain \textit{pseudo paired data} $(\mathcal{Z}, \mathcal{Y})$, and can learn the mapping $G:\mathcal{Z} \mapsto \mathcal{Y}$ in a supervised learning manner. In the inference stage, given a facial photo, we can first transfer it to a line-drawing and then to a sketch by $G \circ F$. Additionally, we propose a novel stroke loss for generating different types of strokes. Our method, termed sRender, accords well with human artists' rendering process. Experimental results demonstrate that sRender can generate multi-style sketches, and significantly outperforms existing unpaired image-to-image translation methods.
Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the amplitude spectrum while reconstructing speech using the mixture phase. Since the clean phase is very important and difficult to predict, the performance of these methods will be limited. Some researchers attempted to estimate the phase spectrum directly or indirectly, but the effect is not ideal. Recently, some studies proposed the complex-valued model and achieved state-of-the-art performance, such as deep complex convolution recurrent network (DCCRN). However, the computation of the model is huge. To reduce the complexity and further improve the performance, we propose a novel method using discrete cosine transform as the input in this paper, called deep cosine transform convolutional recurrent network (DCTCRN). Experimental results show that DCTCRN achieves state-of-the-art performance both on objective and subjective metrics. Compared with noisy mixtures, the mean opinion score (MOS) increased by 0.46 (2.86 to 3.32) absolute processed by the proposed model with only 2.86M parameters.
Photoacoustic (PA) imaging is a biomedical imaging modality capable of acquiring high contrast images of optical absorption at depths much greater than traditional optical imaging techniques. However, practical instrumentation and geometry limit the number of available acoustic sensors surrounding the imaging target, which results in sparsity of sensor data. Conventional PA image reconstruction methods give severe artifacts when they are applied directly to these sparse data. In this paper, we first employ a novel signal processing method to make sparse PA raw data more suitable for the neural network, and concurrently speeding up image reconstruction. Then we propose Attention Steered Network (AS-Net) for PA reconstruction with multi-feature fusion. AS-Net is validated on different datasets, including simulated photoacoustic data from fundus vasculature phantoms and real data from in vivo fish and mice imaging experiments. Notably, the method is also able to eliminate some artifacts present in the ground-truth for in vivo data. Results demonstrated that our method provides superior reconstructions at a faster speed.
Automatic pulmonary nodules classification is significant for early diagnosis of lung cancers. Recently, deep learning techniques have enabled remarkable progress in this field. However, these deep models are typically of high computational complexity and work in a black-box manner. To combat these challenges, in this work, we aim to build an efficient and (partially) explainable classification model. Specially, we use \emph{neural architecture search} (NAS) to automatically search 3D network architectures with excellent accuracy/speed trade-off. Besides, we use the convolutional block attention module (CBAM) in the networks, which helps us understand the reasoning process. During training, we use A-Softmax loss to learn angularly discriminative representations. In the inference stage, we employ an ensemble of diverse neural networks to improve the prediction accuracy and robustness. We conduct extensive experiments on the LIDC-IDRI database. Compared with previous state-of-the-art, our model shows highly comparable performance by using less than 1/40 parameters. Besides, empirical study shows that the reasoning process of learned networks is in conformity with physicians' diagnosis. Related code and results have been released at: https://github.com/fei-hdu/NAS-Lung.
Photoacoustic computed tomography (PACT) reconstructs the initial pressure distribution from raw PA signals. Standard reconstruction always induces artifacts using limited-view signals, which are influenced by limited angle coverage of transducers, finite bandwidth, and uncertain heterogeneous biological tissue. Recently, supervised deep learning has been used to overcome limited-view problem that requires ground-truth. However, even full-view sampling still induces artifacts that cannot be used to train the model. It causes a dilemma that we could not acquire perfect ground-truth in practice. To reduce the dependence on the quality of ground-truth, in this paper, for the first time, we propose a beyond supervised reconstruction framework (BSR-Net) based on deep learning to compensate the limited-view issue by feeding limited-view position-wise data. A quarter position-wise data is fed into model and outputs a group full-view data. Specifically, our method introduces a residual structure, which generates beyond supervised reconstruction result, whose artifacts are drastically reduced in the output compared to ground-truth. Moreover, two novel losses are designed to restrain the artifacts. The numerical and in-vivo results have demonstrated the performance of our method to reconstruct the full-view image without artifacts.
Photoacoustic computed tomography (PACT) reconstructs the initial pressure distribution from raw PA signals. Standard reconstruction always induces artifacts using limited-view signals, which are influenced by limited angle coverage of transducers, finite bandwidth, and uncertain heterogeneous biological tissue. Recently, supervised deep learning has been used to overcome limited-view problem that requires ground-truth. However, even full-view sampling still induces artifacts that cannot be used to train the model. It causes a dilemma that we could not acquire perfect ground-truth in practice. To reduce the dependence on the quality of ground-truth, in this paper, for the first time, we propose a beyond supervised reconstruction framework (BSR-Net) based on deep learning to compensate the limited-view issue by feeding limited-view position-wise data. A quarter position-wise data is fed into model and outputs a group full-view data. Specifically, our method introduces a residual structure, which generates beyond supervised reconstruction result, whose artifacts are drastically reduced in the output compared to ground-truth. Moreover, two novel losses are designed to restrain the artifacts. The numerical and in-vivo results have demonstrated the performance of our method to reconstruct the full-view image without artifacts.
Maintaining a map online is resource-consuming while a robust navigation system usually needs environment abstraction via a well-fused map. In this paper, we propose a mapless planner which directly conducts such abstraction on the unfused sensor data. A limited-memory data structure with a reliable proximity query algorithm is proposed for maintaining raw historical information. A sampling-based scheme is designed to extract the free-space skeleton. A smart waypoint selection strategy enables to generate high-quality trajectories within the resultant flight corridors. Our planner differs from other mapless ones in that it can abstract and exploit the environment information efficiently. The online replan consistency and success rate are both significantly improved against conventional mapless methods.
Due to its superior agility and flexibility, quadrotor is popularly used in challenging environments. In these scenarios, trajectory planning plays a vital role in generating safe motions to avoid obstacles while ensuring flight smoothness. Although many works on quadrotor planning have been proposed, a research gap exists in incorporating self-adaptation into a planning framework to enable a drone to automatically fly slower in denser environments and increase its speed in a safer area. In this paper, we propose an environmental adaptive planner that effectively adjusts the flight aggressiveness based on the obstacle distribution and quadrotor state. Firstly, we design an environmental adaptive safety-aware method to assign the priority of obstacles according to the environmental risk level and instantaneous motion tendency. Then, we apply it into a multi-layered model predictive contouring control framework to generate adaptive, safe, and dynamical feasible local trajectories. Extensive simulations and real-world experiments verify our planning framework's efficiency and robustness and show superior performances in the benchmark comparison. Moreover, we will release our planning framework as open-source ros-packages.