Recently, we have witnessed a boom in applications for 3D talking face generation. However, most existing 3D face generation methods can only generate 3D faces with a static head pose, which is inconsistent with how humans perceive faces. Only a few articles focus on head pose generation, but even these ignore the attribute of personality. In this article, we propose a unified audio-driven approach to endow 3D talking faces with personalized pose dynamics. To achieve this goal, we establish an original person-specific dataset, providing corresponding head poses and face shapes for each video. Our framework is composed of two separate modules: PoseGAN and PGFace. Given an input audio, PoseGAN first produces a head pose sequence for the 3D head, and then, PGFace utilizes the audio and pose information to generate natural face models. With the combination of these two parts, a 3D talking head with dynamic head movement can be constructed. Experimental evidence indicates that our method can generate person-specific head pose sequences that are in sync with the input audio and that best match with the human experience of talking heads.

With the rapid development of artificial intelligence and fifth-generation mobile network technologies, automatic instrument reading has become an increasingly important topic for intelligent sensors in smart cities. We propose a full pipeline to automatically read watermeters based on a single image, using deep learning methods to provide new technical support for an intelligent water meter reading. To handle the various challenging environments where watermeters reside, our pipeline disentangled the task into individual subtasks based on the structures of typical watermeters. These subtasks include component localization, orientation alignment, spatial layout guidance reading, and regression-based pointer reading. The devised algorithms for orientation alignment and spatial layout guidance are tailored to improve the robustness of our neural network. We also collect images of watermeters in real scenes and build a dataset for training and evaluation. Experimental results demonstrate the effectiveness of the proposed method even under challenging environments with varying lighting, occlusions, and different orientations. Thanks to the lightweight algorithms adopted in our pipeline, the system can be easily deployed and fully automated.

It remains an interesting and challenging problem to synthesize a vivid and realistic singing face driven by music. In this paper, we present a method for this task with natural motions for the lips, facial expression, head pose, and eyes. Due to the coupling of mixed information for the human voice and backing music in common music audio signals, we design a decouple-and-fuse strategy to tackle the challenge. We first decompose the input music audio into a human voice stream and a backing music stream. Due to the implicit and complicated correlation between the two-stream input signals and the dynamics of the facial expressions, head motions, and eye states, we model their relationship with an attention scheme, where the effects of the two streams are fused seamlessly. Furthermore, to improve the expressivenes of the generated results, we decompose head movement generation in terms of speed and direction, and decompose eye state generation into short-term blinking and long-term eye closing, modeling them separately. We have also built a novel dataset, SingingFace, to support training and evaluation of models for this task, including future work on this topic. Extensive experiments and a user study show that our proposed method is capable of synthesizing vivid singing faces, qualitatively and quantitatively better than the prior state-of-the-art.

Although remarkable progress has been made in recent years, current multi-exposure image fusion (MEF) research is still bounded by the lack of real ground truth, objective evaluation function, and robust fusion strategy. In this paper, we study the MEF problem from a new perspective. We don’t utilize any synthesized ground truth, design any loss function, or develop any fusion strategy. Our proposed method EMEF takes advantage of the wisdom of multiple imperfect MEF contributors including both conventional and deep learning-based methods. Specifically, EMEF consists of two main stages: pre-train an imitator network and tune the imitator in the runtime. In the first stage, we make a unified network imitate different MEF targets in a style modulation way. In the second stage, we tune the imitator network by optimizing the style code, in order to find an optimal fusion result for each input pair. In the experiment, we construct EMEF from four state-of-the-art MEF methods and then make comparisons with the individuals and several other competitive methods on the latest released MEF benchmark dataset. The promising experimental results demonstrate that our ensemble framework can “get the best of all worlds”. The code is available at https://github.com/medalwill/EMEF.

We present a novel active learning approach for shape co-segmentation based on graph convolutional networks (GCN). The premise of our approach is to represent the collections of 3D shapes as graph-structured data, where each node in the graph corresponds to a primitive patch of an over-segmented shape, and is associated with a representation initialized by extracting features. Then, the GCN operates directly on the graph to update the representation of each node based on a layer-wise propagation rule, which aggregates information from its neighbors, and predicts the labels for unlabeled nodes. Additionally, we further suggest an active learning strategy that queries the most informative samples to extend the initial training samples of GCN, to generate more accurate predictions of our method. Our experimental results on the Shape COSEG Dataset demonstrate the effectiveness of our approach.