In computer graphics, there are three primary research areas: modeling, rendering, and animation, which is generally accepted by graphics practitioners. Modeling deals with the specification of shape and appearance in a way that can be represented mathematically and be stored on the computer. Rendering deals with the creation of shaded images, focusing on interactions between lights and 3D geometric models. Animation creates an illusion of motion through the sequence of images.
Real-Time GPU Rendering and Physically-Based Optical Rendering
Our former studies on lens blur effects and lens flare were successful attempts to prove our belief. Creative combinations of rasterization and ray tracing allowed us to achieve real-time performance and high image quality at the same time. We are still seeking for creative solutions to many open rendering problems.
* Associated grants: NRF Korea, 2012M3A6A3055695
Deep Learning and RenderingDeep learning (DL) allows us to explore many open-problem spaces, in which we usually cannot intuitively obtain a computational model. We are investigating its possibilities in the two aspects
Rendering for DL focuses on the generation of (labeled) images that can be fed into the network as input. This significantly helps to widen the application areas of DL, where we cannot easily attain the input data. To this end, we divert realistic rendering towards imperfect real imagery (CG images are too ideal and clean for this purpose).
Another possibility is DL for rendering. Unlike what it sounds like, DL's mechanism and rendering is contradicting, because many phenomena in the rendering are computationally predictable with explicit models. Instead, we now understand DL as a compact nonlinear modeler for many rendering problems, and explore many possibilities in how it can be effectively utilized modeling-based areas.
Very-High-Resolution GPU ImagingAs 4K and 8K displays become popular, the traditional raster algorithm/pipelines may potentially encounter a bottleneck in the pixel processing. Processing in a native resolution may not be optimal in the near future. To this end, we are investigating how to design a novel pipeline with resolution-independent G-buffers, which encodes geometry and shading information in much lower data-space complexity and reconstructs at a higher resolution without precision loss.
GPU AlgorithmsRendering usually handles a gigantic amount of data. To facilitate rendering, graphics hardware has been rapidly evolving the recent decades. One of the important advances is a user-programmable rendering pipeline. Accordingly, the capability of GPU expands beyond the traditional usage to encompass general-purpose computing. We attempt to achieve improved performance in general computing up to order of two magnitudes. Such an approach is focused on creative algorithms rather than a simple use of GPU and CUDA/OpenCL.
* Associated grants: NRF Korea, 2012R1A2A2A01045719
VR Illumination and Display AlgorithmsReal-time global illumination for virtual reality (VR) and augmented reality (AR) requires to be computed with hard real-time constraints, usually higher than 60 frames per sec. We are trying to develop efficient techniques to achieve visually plausible and temporally coherent appearances. In particular, volume-based approximation of global illumination techniques are improved. Also, the global illumination techniques for pure VR are extended to AR with efficient acquisition of scene geometry, light sources, and materials from input video streams.
Stereoscopic (binocular) display needs to be employed to mediate interactive VR/AR experiences. Such display devices still incur visual fatigues in many optical and perceptual aspects. To cope with these problems, we are investigating how to improve optical accuracy of VR display in terms of motion blur and optical aberrations.
TeeVR (Third Eye Everywhere VR), a collaborative project with Perceptional Robotics Lab., Korea University, is our another attempt to realize high-quality VR/AR experiences. The key elements for TeeVR include high-quality acquisition of real-world geometries and synthesis of novel views from panoramic captures. This projects aims to surpass the classical image-based rendering techniques in terms of temporal coherence.
* Associated grants: NRF Korea, 2012M3A6A3055695, Samsung Electronics 2016, ITRC for Mobile VR
Perception-Based VisualizationEffective visualization of informative data involves in-depth understandings on human visual perception. Unlike common approaches based on image analysis, our research advances more to image synthesis solutions, leading to perceptually-effective visualization. Visual saliency is one of the important keys to such approaches.
* Associated grants: NRF Korea, 2011-0014015