Generating a rendered image sequence through Monte Carlo ray tracing is an appealing option when one aims to accurately simulate various lighting effects. Unfortunately, interactive rendering scenarios limit the allowable sample size for such sampling-based light transport algorithms, resulting in an unbiased but noisy image sequence. Image denoising has been widely adopted as a post-sampling process to convert such noisy image sequences into biased but temporally stable ones. The state-of-the-art strategy for interactive image denoising involves devising a deep neural network and training this network via supervised learning, i.e., optimizing the network parameters using training datasets that include an extensive set of image pairs (noisy and ground truth images). This paper adopts the prevalent approach for interactive image denoising, which relies on a neural network. However, instead of supervised learning, we propose a different learning strategy that trains our network parameters on the fly, i.e., updating them online using runtime image sequences. To achieve our denoising objective with online learning, we tailor local regression to a cross-regression form that can guide robust training of our denoising neural network. We demonstrate that our denoising framework effectively reduces noise in input image sequences while robustly preserving both geometric and non-geometric edges, without requiring the manual effort involved in preparing an external dataset.

Abstract Photon mapping is a light transport algorithm that simulates various rendering effects (e.g., caustics) robustly, and its progressive variants, progressive photon mapping (PPM) methods, can produce a biased but consistent rendering output. PPM estimates radiance using a kernel density estimation whose parameters (bandwidths) are adjusted progressively, and this refinement enables to reduce its estimation bias. Nonetheless, many iterations (and thus a large number of photons) are often required until PPM produces nearly converged estimates. This paper proposes a post‐reconstruction that improves the performance of PPM by reducing residual errors in PPM estimates. Our key idea is to take multiple PPM estimates with multi‐level correlation structures, and fuse the input images using a weight function trained by supervised learning with maintaining the consistency of PPM. We demonstrate that our technique boosts an existing PPM technique for various rendering scenes.

We have developed User Enactments to help support design teams in more successfully investigating radical alterations to technologies' roles, forms and behaviors in uncharted design spaces. To date, no work exists that explicitly unpacks the practical development of a cohesive set of user enactments. Interest is growing in the method with its recent inclusion in a popular design method handbook for practitioners and also as it becomes integrated into graduate-level university curriculum in interaction design. The contribution of this Pictorial is to unpack the thinking and making behind a set of user enactments through visual documentation and annotations.

Over the past several years, people have acquired more and more virtual possessions. While virtual possessions have become ubiquitous, little work exists to inform designers on how these growing collections should be displayed and how they should behave. We generated four design concepts that changed the form and behavior of these digital things, making them more present within a teen bedroom. We then conducted speed dating sessions to investigate how these new forms and behaviors influence perceptions of value. Sessions revealed how new technologies might better support self-exploration and reflection, as well as how they could complicate identity construction processes. Findings are interpreted to detail opportunities and tensions that can guide future research and practice in this emerging space.