Many cephalopods such as octopus and squid change their skin color purposefully within a very short time. Furthermore, it is widely known that some octopuses have the ability to change the color and unevenness of the skin and to mimic the surroundings in short time. However, much research has not been done on the entire mimicry mechanism in which the octopus recognizes the surrounding landscape and changes the skin pattern. It seems that there is no hypothetical model to explain the whole mimicry mechanism yet. In this study, the mechanism of octopus skin pattern formation was assumed to be based on the Turing model. Here, the pattern formation by the Turing model was realized by the equivalent filter calculation model using the cellular automaton, instead of directly solving the differential equations. It was shown that this model can create various patterns with two feature parameters. Furthermore, for the eyes recognition part where two features are extracted from the Turing pattern image, our study proposed a method that can be calculated back with small amount of calculation using the characteristics of the cellular Turing pattern model. These two calculations can be expressed in the same mathematical frame based on the cellular automaton model using the convolution filter. As a result, it can be created a model which is capable of extracting features from patterns and reconstructing patterns in a short time, the model is considered to be a basic model for considering the mimicry mechanism of octopus. Also, in terms of application to machine learning, it is considered that it shows the possibility of leading to a model with a small amount of learning calculation.
This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The participants had to render bokeh effect based on only one single frame without any additional data from other cameras or sensors. The target metric used in this challenge combined the runtime and the perceptual quality of the solutions measured in the user study. To ensure the efficiency of the submitted models, we measured their runtime on standard desktop CPUs as well as were running the models on smartphone GPUs. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical bokeh effect rendering problem.
There have been many discriminative learning methods using convolutional neural networks (CNN) for several image restoration problems, which learn the mapping function from a degraded input to the clean output. In this letter, we propose a self-committee method that can find enhanced restoration results from the multiple trial of a trained CNN with different but related inputs. Specifically, it is noted that the CNN sometimes finds different mapping functions when the input is transformed by a reversible transform and thus produces different but related outputs with the original. Hence averaging the outputs for several different transformed inputs can enhance the results as evidenced by the network committee methods. Unlike the conventional committee approaches that require several networks, the proposed method needs only a single network. Experimental results show that adding an additional transform as a committee always brings additional gain on image denoising and single image supre-resolution problems.
We propose a computational framework for ranking images (group photos in particular) taken at the same event within a short time span. The ranking is expected to correspond with human perception of overall appeal of the images. We hypothesize and provide evidence through subjective analysis that the factors that appeal to humans are its emotional content, aesthetics and image quality. We propose a network which is an ensemble of three information channels, each predicting a score corresponding to one of the three visual appeal factors. For group emotion estimation, we propose a convolutional neural network (CNN) based architecture for predicting group emotion from images. This new architecture enforces the network to put emphasis on the important regions in the images, and achieves comparable results to the state-of-the-art. Next, we develop a network for the image ranking task that combines group emotion, aesthetics and image quality scores. Owing to the unavailability of suitable databases, we created a new database of manually annotated group photos taken during various social events. We present experimental results on this database and other benchmark databases whenever available. Overall, our experiments show that the proposed framework can reliably predict the overall appeal of images with results closely corresponding to human ranking.
Object 6D pose estimation is an important research topic in the field of computer vision due to its wide application requirements and the challenges brought by complexity and changes in the real-world. We think fully exploring the characteristics of spatial relationship between points will help to improve the pose estimation performance, especially in the scenes of background clutter and partial occlusion. But this information was usually ignored in previous work using RGB image or RGB-D data. In this paper, we propose a framework for 6D pose estimation from RGB-D data based on spatial structure characteristics of 3D keypoints. We adopt point-wise dense feature embedding to vote for 3D keypoints, which makes full use of the structure information of the rigid body. After the direction vectors pointing to the keypoints are predicted by CNN, we use RANSAC voting to calculate the coordinate of the 3D keypoints, then the pose transformation can be easily obtained by the least square method. In addition, a spatial dimension sampling strategy for points is employed, which makes the method achieve excellent performance on small training sets. The proposed method is verified on two benchmark datasets, LINEMOD and OCCLUSION LINEMOD. The experimental results show that our method outperforms the state-of-the-art approaches, achieves ADD(-S) accuracy of 98.7\% on LINEMOD dataset and 52.6\% on OCCLUSION LINEMOD dataset in real-time.
Numerical integration is a foundational technique in scientific computing and is at the core of many computer vision applications. Among these applications, implicit neural volume rendering has recently been proposed as a new paradigm for view synthesis, achieving photorealistic image quality. However, a fundamental obstacle to making these methods practical is the extreme computational and memory requirements caused by the required volume integrations along the rendered rays during training and inference. Millions of rays, each requiring hundreds of forward passes through a neural network are needed to approximate those integrations with Monte Carlo sampling. Here, we propose automatic integration, a new framework for learning efficient, closed-form solutions to integrals using implicit neural representation networks. For training, we instantiate the computational graph corresponding to the derivative of the implicit neural representation. The graph is fitted to the signal to integrate. After optimization, we reassemble the graph to obtain a network that represents the antiderivative. By the fundamental theorem of calculus, this enables the calculation of any definite integral in two evaluations of the network. Using this approach, we demonstrate a greater than 10x improvement in computation requirements, enabling fast neural volume rendering.
The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process. The landmark SketchRNN provided breakthrough by sequentially generating sketches as a sequence of waypoints. However this leads to low-resolution image generation, and failure to model long sketches. In this paper we present B\'ezierSketch, a novel generative model for fully vector sketches that are automatically scalable and high-resolution. To this end, we first introduce a novel inverse graphics approach to stroke embedding that trains an encoder to embed each stroke to its best fit B\'ezier curve. This enables us to treat sketches as short sequences of paramaterized strokes and thus train a recurrent sketch generator with greater capacity for longer sketches, while producing scalable high-resolution results. We report qualitative and quantitative results on the Quick, Draw! benchmark.
In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L2 norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular hand-crafted descriptors, such as SIFT. According to the results, our approach outperforms state-of-the-art L2-based descriptors and can be considered as a direct replacement of SIFT. In addition, we conducted experiments with batch normalization and histogram equalization as a preprocessing method of the input data. The results confirm that these techniques further improve the performance of the proposed descriptor. Finally, we show promising preliminary results by appending our CNNs with recently proposed spatial transformer networks and provide a visualisation and interpretation of their impact.
We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it explicitly represents the 2D position and depth of each object, as well as an embedding of its segmentation mask and appearance. The model can be trained from images alone in a purely unsupervised fashion without the need for object masks or depth information. Moreover, it always generates complete objects, even though a significant fraction of training images contain occlusions. Finally, we show that our model can infer decompositions of novel images into their constituent objects, including accurate prediction of depth ordering and segmentation of occluded parts.
Full-reference (FR) point cloud quality assessment (PCQA) has achieved impressive progress in recent years. However, in many cases, obtaining the reference point cloud is difficult, so the no-reference (NR) methods have become a research hotspot. Since learning-based FR-PCQA methods should be driven by data, few researches about NR objective quality metrics are conducted due to lack of large-scale subjective point cloud dataset. The shortage of point cloud data restricts the development of NR-PCQA techniques. Besides, the distinctive property of point cloud format makes infeasible applying blind image quality assessment (IQA) methods directly to predict the quality scores of point clouds. In this paper, we establish a large-scale PCQA dataset, which includes 104 reference point clouds and more than 24,000 distorted point clouds. In the established dataset, each reference point cloud is augmented with 34 types of impairments (e.g., Gaussian noise, contrast distortion, geometry noise, local loss, and compression loss) at 7 different distortion levels. Besides, inspired by the hierarchical perception system and considering the intrinsic attribute of point clouds, an end-to-end sparse convolutional neural network (CNN) is designed to accurately estimate the subjective quality. We conduct experiments on the new dataset to evaluate the performance of the proposed network. The results demonstrate that the proposed network has reliable performance. The dataset presented in this work will be publicly accessible at http://smt.sjtu.edu.cn.