Regression and deep learning for photorealistic rendering
As a primary research theme, we have actively studied regression and learning techniques that estimate the ground truth image from sparse (noisy) samples to generate photo-realistic rendering images more efficiently. We have recently developed novel local regression-based techniques and deep-learning methods that significantly improve the quality of rendering images generated by Monte Carlo ray-tracing algorithms (e.g., path tracing).
Photorealistic rendering in augmented reality (AR)
Visually integrating virtual objects into real environments is a crucial ingredient for photo-realistic augmented reality (AR). We have worked on novel techniques that capture the real scene's illumination and interactively render virtual objects using the estimated light to accomplish the research goal.
Acceleration for ray tracing
Ray tracing is a core technology that has been widely adopted for photo-realistic light transport algorithms. However, it requires computationally expensive operations (e.g., ray-box or ray-triangle intersections). We aim at accelerating the core technique using a variety of optimizations such as ray reordering.
