We propose an automatic framework for quality assessment of a photograph as well as analysis of its aesthetic attributes. In contrast to the previous methods that rely on manually designed features to account for photo aesthetics, our method automatically extracts such features using a pretrained deep convolutional neural network (DCNN). To make the DCNN-extracted features more suited to our target tasks of photo quality assessment and aesthetic attribute analysis, we propose a novel feature encoding scheme, which supports vector machines-driven sparse restricted Boltzmann machines, which enhances sparseness of features and discrimination between target classes. Experimental results show that our method outperforms the current state-of-the-art methods in automatic photo quality assessment, and gives aesthetic attribute ratings that can be used for photo editing. We demonstrate that our feature encoding scheme can also be applied to general object classification task to achieve performance gains.

Abstract This paper presents a novel method to enhance the performance of structure‐preserving image and texture filtering. With conventional edge‐aware filters, it is often challenging to handle images of high complexity where features of multiple scales coexist. In particular, it is not always easy to find the right balance between removing unimportant details and protecting important features when they come in multiple sizes, shapes, and contrasts. Unlike previous approaches, we address this issue from the perspective of adaptive kernel scales. Relying on patch‐based statistics, our method identifies texture from structure and also finds an optimal per‐pixel smoothing scale. We show that the proposed mechanism helps achieve enhanced image/texture filtering performance in terms of protecting the prominent geometric structures in the image, such as edges and corners, and keeping them sharp even after significant smoothing of the original signal.

Abstract We introduce an affective image recoloring method for changing the overall mood in the image in a numerically measurable way. Given a semantically segmented source image and a target emotion, our system finds reference image segments from the collection of images that have been tagged via crowdsourcing with numerically measured emotion labels. We then recolorize the source segments using colors from the selected target segments while preserving the gradient of the source image to generate a seamless and natural result. User study confirms the effectiveness of our method in accomplishing the stated goal of altering the mood of the image to match the target emotion level.

Abstract Color assignment is a complex task of incorporating and balancing area configuration, color harmony, and user's intent. In this paper, we present a novel method for automatic color assignment based on theories of color perception. We define color assignment as an optimization problem with respect to the color relationships as well as the spatial configuration of input segments. We also suggest possible constraints that are suitable for task‐specific purposes and for enhancing visual appeal. Our colorization scheme is useful in many applications such as infographics, computer‐aided design, and visual presentation. The user study shows that our method generates perceptually pleasing results over a variety of data sets.

Abstract We present a novel method for enhancing details in a digital photograph, inspired by the principle of art photography. In contrast to the previous methods that primarily rely on tone scaling, our technique provides a flexible tone transform model that consists of two operators: shifting and scaling. This model permits shifting of the tonal range in each image region to enable significant detail boosting regardless of the original tone. We optimize these shift and scale factors in our constrained optimization framework to achieve extreme detail enhancement across the image in a piecewise smooth fashion, as in art photography. The experimental results show that the proposed method brings out a significantly large amount of details even from an ordinary low‐dynamic range image.

This paper presents a novel structure-preserving image decomposition operator called bilateral texture filter . As a simple modification of the original bilateral filter [Tomasi and Manduchi 1998], it performs local patch-based analysis of texture features and incorporates its results into the range filter kernel. The central idea to ensure proper texture/structure separation is based on patch shift that captures the texture information from the most representative texture patch clear of prominent structure edges. Our method outperforms the original bilateral filter in removing texture while preserving main image structures, at the cost of some added computation. It inherits well-known advantages of the bilateral filter, such as simplicity, local nature, ease of implementation, scalability, and adaptability to other application scenarios.

Stereoscopic 3D exploits the effects of stereopsis where the depth perception is triggered by binocular disparity, a difference in image location of an object by the left and right eyes. Despite the dissimilarity of stereo projections in terms of disparity and shape, the human visual system can find the matching stereo pair to fuse using their similarities in terms of color, size, shading, texture, shadows, that are normally present in photorealistic stereo imaging. Now if some of these elements (or depth cues) are missing, such as in non-photorealistic stereo imaging, how will it affect the depth perception and stereo fusion? In this paper, we investigate this issue by conducting a perceptual study on stereoscopic 3D line drawing, in which many of these cues have been abstracted away. We first evaluate the validity of using stereo images composed of lines only, and then compare its performance to stereo images of normal shading. We also examine the effect of changing line style as well as the prospect of using lines as an additional depth cue. Our study shows that stereo line drawing, when compared to stereo shading, does weaken the depth perception but only to a minor degree. On the other hand, modification of line style, and superimposition of stereo lines both have potentials to strengthen the perception of depth.

This paper discusses stereoscopic 3D imaging based on line drawing of 3D shapes. We describe the major issues and challenges in generating stereoscopic 3D effects using lines only, with a couple of relatively simple approaches called each-eye-based and center-eye-based. Each of these methods has its shortcomings, such as binocular rivalry and inaccurate lines. We explain why and how these problems occur, then describe the concept of stereo-coherent lines and an algorithm to extract them from 3D shapes. We also propose a simple method to stylize stereo lines that ensures the stereo coherence of stroke textures across binocular views. The proposed method provides viewers with unique visual experience of watching 2D drawings popping out of the screen like 3D.

We present a method for constructing 3D feature flow from video and its application to video stylization. Our method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner. As an application of this flow field we present a particle-based video stylization technique to rerender the video in a feature enhancing, painterly style. Our method consists of per-pixel operations and is suitable for GPU implementation, which enables real-time video stylization.

Abstract In this work, we present a non‐photorealistic rendering technique to create stylized abstractions from color images and videos. Our approach is based on adaptive line integral convolution in combination with directional shock filtering. The smoothing process regularizes directional image features while the shock filter provides a sharpening effect. Both operations are guided by a flow field derived from the structure tensor. To obtain a high‐quality flow field, we present a novel smoothing scheme for the structure tensor based on Poisson's equation. Our approach effectively regularizes anisotropic image regions while preserving the overall image structure and achieving a consistent level of abstraction. Moreover, it is suitable for per‐frame filtering of video and can be efficiently implemented to process content in real‐time.

Abstract We present a non‐photorealistic rendering technique to transform color images and videos into painterly abstractions. It is based on a generalization of the Kuwahara filter that is adapted to the local shape of features, derived from the smoothed structure tensor. Contrary to conventional edge‐preserving filters, our filter generates a painting‐like flattening effect along the local feature directions while preserving shape boundaries. As opposed to conventional painting algorithms, it produces temporally coherent video abstraction without extra processing. The GPU implementation of our method processes video in real‐time. The results have the clearness of cartoon illustrations but also exhibit directional information as found in oil paintings.

We present a non-photorealistic rendering technique that automatically delivers a stylized abstraction of a photograph. Our approach is based on shape/color filtering guided by a vector field that describes the flow of salient features in the image. This flow-based filtering significantly improves the abstraction performance in terms of feature enhancement and stylization. Our method is simple, fast, and easy to implement. Experimental results demonstrate the effectiveness of our method in producing stylistic and feature-enhancing illustrations from photographs.

Abstract This paper presents a simple algorithm for producing stylistic abstraction of a photograph. Based on mean curvature flow in conjunction with shock filter, our method simplifies both shapes and colors simultaneously while preserving important features. In particular, we develop a constrained mean curvature flow, which outperforms the original mean curvature flow in conveying the directionality of features and shape boundaries. The proposed algorithm is iterative and incremental, and therefore the level of abstraction is intuitively controlled. Optionally, simple user masking can be incorporated into the algorithm to selectively control the abstraction speed and to protect particular regions. Experimental results show that our method effectively produces highly abstract yet feature‐preserving illustrations from photographs.

Abstract This paper presents an automatic method for producing stipple renderings from photographs, following the style of professional hedcut illustrations. For effective depiction of image features, we introduce a novel dot placement algorithm which adapts stipple dots to the local shapes. The core idea is to guide the dot placement along ‘feature flow’ extracted from the feature lines, resulting in a dot distribution that conforms to feature shapes. The sizes of dots are adaptively determined from the input image for proper tone representation. Experimental results show that such feature‐guided stippling leads to the production of stylistic and feature‐emphasizing dot illustrations.

Abstract A hidden‐picture puzzle contains objects hidden in a background image, in such a way that each object fits closely into a local region of the background. Our system converts image of the background and objects into line drawing, and then finds places in which to hide transformed versions of the objects using rotation‐invariant shape context matching. During the hiding process, each object is subjected to a slight deformation to enhance its similarity to the background. The results were assessed by a panel of puzzle‐solvers.

We present a novel scheme for automatically generating line drawings from 2D images, aiming to facilitate effective visual communication. In contrast to conventional edge detectors, our technique imitates the human line drawing process and consists of two parts: line extraction and line rendering. We propose a novel line extraction method based on likelihood-function estimation, which effectively finds the genuine shape boundaries. We consider the feature scale and the blurriness of lines with which the detail and the focus-level of lines are controlled in the rendering. We also employ stroke textures to provide a variety of illustration styles. Experimental results demonstrate that our technique generates various kinds of line drawings from 2D images enabled by the control over detail, focus, and style.