Ray prioritization using stylization and visual saliency

Abstract

Figure 1: Four different scenarios rendered with a conventional ray-based rendering engine and with the presented adaptive approach in a 1024 × 768 viewport. (a) shows the areas in which the rays are fully computed (left) and the resulting reconstruction by our algorithm (right). (b) shows how our approach can boost the frame rate while preserving the quality level. Our algorithm can also be applied to ray-tracing scenes with complex materials (c). Priority sorting of the expected visual quality of a pixel allows us to guarantee frame rates for every type of ray-based environment while maintaining a visually appealing result (d). Selected non-obvious artifacts, which are introduced by using our method for guaranteed frame rates, are marked with small arrows in (c) and (d). AbstractThis paper presents a new method to control graceful scene degradation in complex ray-based rendering environments. It proposes to constrain the image sampling density with object features, which are known to support the comprehension of the three-dimensional shape. The presented method uses Non-Photorealistic Rendering (NPR) techniques to extract features such as silhouettes, suggestive contours, suggestive highlights, ridges and valleys. To map different feature types to sampling densities, we also present an evaluation of the features impact on the resulting image quality. To reconstruct the image from sparse sampling data, we use linear interpolation on an adaptively aligned fractal pattern. With this technique, we are able to present an algorithm that guarantees a desired minimal frame rate without much loss of image quality. Our scheduling algorithm maximizes the use of each given time slice by rendering features in order of their corresponding importance values until a time constraint is reached. We demonstrate how our method can be used to boost and guarantee the rendering time in complex raybased environments consisting of geometric as well as volumetric data.

TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction

“…Saliency prediction algorithms aim to computationally detect these regions that stand out relative to their surroundings. These predictions have numerous applications in image compression [34], image enhancement [48], image retargeting [1], rendering [40], and segmentation [26].…”

An Architecture Approach for 3D Render Distribution using Mobile Devices in Real Time

“…Another algorithm commonly used for rendering is Ray-tracing [15,16,17,25,26,27,28]. This is based on the illumination of the image, capturing the beam size and its reflection on the object.…”

Special section on the 2011 joint symposium on computational aesthetics (CAe), non-photorealistic animation and rendering (NPAR), and sketch-based interfaces and modeling (SBIM)

“…The final extended paper within the NPAR section of this issue is unusual among those commonly appearing at these symposia, given the focus on maintaining photorealism in rendering. "Ray Prioritization Using Stylization and Visual Saliency" [9] presents a new approach for maintaining photorealistic detail in scene rendering, to achieve a guaranteed frame rate when rendering complex scenes. This is achievable through their exploitation of non-photorealistic cues in the rendering process.…”