Regression based Reconstruction

Our lab is designing various regression based reconstruction techniques. Some of examples include:

  • Regression based image-space filtering techniques for accelerating Monte Carlo ray tracing techniques.
  • Computing useful features guiding the regression process
  • Regression techniques for gradient-domain rendering method
Gradient Outlier Removal for Gradient‐Domain Path Tracing
Saerom Ha, Sojin Oh, Jonghee Back, Sung-Eui Yoon, and Bochang Moon
Eurographics, 2019
Feature Generation for Adaptive Gradient-Domain Path Tracing
Jonghee Back, Sung-Eui Yoon, and Bochang Moon
Pacific Graphics(PG), 2018
Received best paper honorable mention award
Adaptive Rendering with Linear Predictions
Bochang Moon, Jose A. Iglesias-Guitian, Sung-Eui Yoon, and Kenny Mitchell
TopACM Transaction on Graphics (Proc. of SIGGRAPH), 2015
Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering
M. Zwicker, W. Jarosz, J. Lehtinen, B. Moon, R. Ramamoorthi, F. Rousselle, P. Sen, C. Soler, and S.-E. Yoon
State of The Art Report, EG (CGF), 2015
Adaptive Rendering based on Weighted Local Regression
Bochang Moon, Nathan Carr, and Sung-Eui Yoon
ACM Transactions on Graphics, 2014
P-RPF: Pixel-based Random Parameter Filtering for Monte Carlo Rendering
Hyosub Park, Bochang Moon, Soomin Kim, and Sung-Eui Yoon
CAD/Graphics, 2013
Robust Image Denoising using a Virtual Flash Image for Monte Carlo Ray Tracing
Bochang Moon, Jong Yun Jun, JongHyeob Lee, Kunho Kim, Toshiya Hachisuka, and Sung-Eui Yoon
Computer Graphics Forum (2013), Vol. 32, number 1, pp. 139-151., 2013