Abstract Real‐time path tracing for global illumination has recently become feasible on high‐performance desktop GPUs, but achieving similar performance on mobile platforms remains a significant challenge due to computational limitations. As mobile devices begin to integrate ray tracing capabilities, new methods are required to bridge the performance gap and enable advanced rendering techniques on constrained hardware. In this paper, we present Mobile Radiance Caching (MobileRC), an online trainable radiance caching approach based on a plenoxel representation, designed to accelerate path tracing on mobile devices. Unlike neural network‐based radiance caching methods, which rely on matrix multiplication accelerators unavailable on current mobile GPUs, MobileRC uses a voxel‐based representation where each voxel stores spherical harmonic coefficients to represent angular dependencies, making it more suitable for mobile hardware. Specifically, we exploit the localized interaction between learnable plenoxel weights and training samples, designing a mobile‐friendly training method. While our approach incurs a mild loss in cache quality compared to neural methods optimized for high‐end GPUs, it significantly improves image quality while reducing rendering time, achieving interactive frame rates for full HD images in room‐sized scenes on mobile hardware.

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.

Temporal interpolation often plays a crucial role to learn meaningful representations in dynamic scenes. In this paper, we propose a novel method to train spatiotemporal neural radiance fields of dynamic scenes based on temporal interpolation of feature vectors. Two feature interpolation methods are suggested depending on underlying representations, neural networks or grids. In the neural representation, we extract features from space-time inputs via multiple neural network modules and interpolate them based on time frames. The proposed multi-level feature interpolation network effectively captures features of both short-term and long-term time ranges. In the grid representation, space-time features are learned via four-dimensional hash grids, which remarkably reduces training time. The grid representation shows more than 100x faster training speed than the previous neural-net-based methods while maintaining the rendering quality. Concatenating static and dynamic features and adding a simple smoothness term further improve the performance of our proposed models. Despite the simplicity of the model architectures, our method achieved state-of-the-art performance both in rendering quality for the neural representation and in training speed for the grid representation.

We introduce a Large Scale Multi-Illuminant (LSMI) Dataset that contains 7,486 images, captured with three different cameras on more than 2,700 scenes with two or three illuminants. For each image in the dataset, the new dataset provides not only the pixel-wise ground truth illumination but also the chromaticity of each illuminant in the scene and the mixture ratio of illuminants per pixel. Images in our dataset are mostly captured with illuminants existing in the scene, and the ground truth illumination is computed by taking the difference between the images with different illumination combination. Therefore, our dataset captures natural composition in the real-world setting with wide field-of-view, providing more extensive dataset compared to existing datasets for multi-illumination white balance. As conventional single illuminant white balance algorithms cannot be directly applied, we also apply per-pixel DNN-based white balance algorithm and show its effectiveness against using patch-wise white balancing. We validate the benefits of our dataset through extensive analysis including a user-study, and expect the dataset to make meaningful contribution for future work in white balancing.

Abstract In this paper, we present a novel SPH framework to simulate incompressible fluid that satisfies both the divergence‐ free condition and the density‐invariant condition. In our framework, the two conditions are applied separately. First, the divergence‐free condition is enforced when solving the momentum equation. Later, the density‐invariant condition is applied after the time integration of the particle positions. Our framework is a purely Lagrangian approach so that no auxiliary grid is required. Compared to the previous density‐invariant based SPH methods, the proposed method is more accurate due to the explicit satisfaction of the divergence‐free condition. We also propose a modified boundary particle method for handling the free‐slip condition. In addition, two simple but effective methods are proposed to reduce the particle clumping artifact induced by the density‐invariant condition.

In this paper, an interactive medical image visualization system to support medical therapy has been introduced, where 3D organ model with the corresponding medical image is visualized interactively for diagnosis and surgical planning. To show effectiveness of the proposed system, 3D liver model generated from CT data has been utilized in consideration of its deformable characteristics by respiration as well as appearance. In addition, a hand gesture interface is applied on the graphical user interface for providing more natural and intuitive interactivity.

Abstract This paper presents a hybrid approach to multiple fluid simulation that can handle miscible and immiscible fluids, simultaneously. We combine distance functions and volume fractions to capture not only the discontinuous interface between immiscible fluids but also the smooth transition between miscible fluids. Our approach consists of four steps: velocity field computation, volume fraction advection, miscible fluid diffusion, and visualization. By providing a combining scheme between volume fractions and level set functions, we are able to take advantages of both representation schemes of fluids. From the system point of view, our work is the first approach to Eulerian grid‐based multiple fluid simulation including both miscible and immiscible fluids. From the technical point of view, our approach addresses the issues arising from variable density and viscosity together with material diffusion. We show that the effectiveness of our approach to handle multiple miscible and immiscible fluids through experiments.

Abstract Conventional level set‐based approaches have an inherent difficulty in tracking miscible fluids due to its discrete treatment for interface. This paper proposes a unified framework to efficiently handle both miscible and immiscible fluid simulations. Based on the chemical potential energy, our method describes the evolution of multiple fluids as time‐varying concentration fields. Handling of multiple fluids is straightforward and, unlike level set methods, ad hoc reinitialization or fictitious particle deployment is not necessary. For numerical computation of the Navier—Stokes equations, we adopt advanced lattice Boltzmann methods (LBMs) for computational efficiency. The experiments show that our approach works well with immiscible fluids, miscible fluids, and interaction with objects. Copyright © 2008 John Wiley & Sons, Ltd.