Search Results

Existing Neural Architecture Search algorithms achieve a low error rate in vision tasks, such as image classification, by training child networks with equal resources during the search. However, it is unnecessary to allocate equal resources or ...

This paper presents the first method for synthesizing seasonal transition of terrain textures for an input heightfield. Our method reproduces a seamless transition of terrain textures according to the seasons by learning measured data on the earth ...

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through ...

Conditional Generative Adversarial Networks (CGANs) are well developed on balanced datasets as default standards for generating high-quality images of expected classes. However, the common problem in practice is that training datasets are ...

Line drawing is a form of painting that uses lines as expressive elements and often employs the combination of abstraction and figuration (CAF) technique to enhance artistic expression. However, existing methods tend to focus on generating semantically ...

Facial age transformation methods can change facial appearance according to the target age. However, most existing methods do not consider that people get older with different attribute changes (e.g., wrinkles, hair volume, and face shape) ...

Highly accurate self-localization is necessary to achieve safe autonomous driving. Recently, map-based self-localization has been attracting attention. Maps generally consist of point cloud information and vector information. However, this information is ...

A high definition (HD) map, which provides prior knowledge to autonomous driving tasks, has been attracted in recent years. An HD map-based self-localization is a crucial technology for autonomous driving, but its accuracy is greatly affected by ...

Automatic generation of a high-quality video from a single image remains a challenging task despite the recent advances in deep generative models. This paper proposes a method that can create a high-resolution, long-term animation using convolutional ...

Relighting of human images has various applications in image synthesis. For relighting, we must infer albedo, shape, and illumination from a human portrait. Previous techniques rely on human faces for this inference, based on spherical harmonics (SH) ...

Inferring a high dynamic range (HDR) image from a single low dynamic range (LDR) input is an ill-posed problem where we must compensate lost data caused by under-/over-exposure and color quantization. To tackle this, we propose the first deep-learning-...

Human parsing is a fundamental task to estimate semantic parts in a human image such as face, arm, leg, hat, and dress. Recent deep-learning based methods have achieved significant improvements, but collecting training datasets of pixel-wise annotations ...

This paper presents an efficient approach for generating weathering effects with detailed appearance variations in a single image. Previous approaches merely change chroma or reflectance of weathered objects, which is not sufficient for materials with ...

Edit propagation is a technique that can propagate various image edits (e.g., colorization and recoloring) performed via user strokes to the entire image based on similarity of image features. In most previous work, users must manually determine the ...

This paper addresses the problem of feature extraction for estimating users' transportation modes from their movement trajectories. Previous studies have adopted supervised learning approaches and used engineers' skills to find effective features for ...

Sequencing the whole genome of various species has many applications, not only in understanding biological

systems, but also in medicine, pharmacy, and agriculture. In recent years, the emergence of high-throughput

next generation sequencing ...

Analyzing emerging topics from social media enables users to overview social movement and several web services to adopt current trends. Although existing studies mainly focus on extracting global emerging topics, efficient extraction of local ones ...

We propose an image editing system for repositioning objects in a single image based on the perspective of the scene. In our system, an input image is transformed into a layer structure that is composed of object layers and a background layer, and then ...

In this paper, we propose an interactive technique for constructing a 3D scene via sparse user inputs. We represent a 3D scene in the form of a Layered Depth Image LDI which is composed of a foreground layer and a background layer, and each layer has a ...

Determining whole genome sequences of various species has many applications not only in biological system,

but also in medicine, pharmacy and agriculture. In recent years, the emergence of high-throughput next generation

sequencing technologies has ...