Baking Neural Radiance Fields for Real-Time View Synthesis.

Neural volumetric representations such as Neural Radiance Fields (NeRF) have emerged as a compelling technique for learning to represent 3D scenes from images with the goal of rendering photorealistic images of the scene from unobserved viewpoints. However, NeRF's computational requirements are prohibitive for real-time applications: rendering views from a trained NeRF requires querying a multilayer perceptron (MLP) hundreds of times per ray. We present a method to train a NeRF, then precompute and store (i.e. "bake") it as a novel representation called a Sparse Neural Radiance Grid (SNeRG) that enables real-time rendering on commodity hardware. To achieve this, we introduce 1) a reformulation of NeRF's architecture, and 2) a sparse voxel grid representation with learned feature vectors. The resulting scene representation retains NeRF's ability to render fine geometric details and view-dependent appearance, is compact (averaging less than 90 MB per scene), and can be rendered in real-time (higher than 30 frames per second on a laptop GPU). Actual screen captures are shown in our video.

Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields.

Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.

Swedish guidelines for registry-based randomized clinical trials.

During the last decade Sweden has invested in a national infrastructure for collection of structured clinical data in the form of healthcare registries (in Sweden known as Kvalitetsregister). These data can be combined with other public data using the national personal identifiers that are issued to Swedish citizens. The healthcare registries have an almost complete coverage of Swedish healthcare, and a large network of clinicians is involved in the quality assurance and continuous improvement of healthcare using these registries. Uppsala Clinical Research Center (UCR) has been a technology provider of large-scale national registries and has a strong background in clinical trial management. This effort combines the areas of healthcare registries and clinical trials into a novel way of performing clinical trials to be able to: 1) run clinical trials as an integrated part of normal clinic workflow; and 2) leverage the nationwide network of outcome reporting. This strategy was shown to be successful in the TASTE (Thrombus Aspiration in Myocardial Infarction) study. When TASTE had been published, the New England Journal of Medicine wrote a perspective on the study calling it 'The randomized registry trial-the next disruptive technology in clinical research?' Since then several studies have been conducted in this way with great success. UCR has been appointed, by Clinical Studies Sweden and the Swedish Research Council, to develop the Swedish national guidelines for registry-based randomized clinical trials in order to ensure the possibility for more organizations to run this kind of study. This paper describes key concepts of register-based randomized clinical trials and the development of Swedish national guidelines.

Sequential Monte Carlo Instant Radiosity.

Instant Radiosity and its derivatives are interactive methods for efficiently estimating global (indirect) illumination. They represent the last indirect bounce of illumination before the camera as the composite radiance field emitted by a set of virtual point light sources (VPLs). In complex scenes, current algorithms suffer from a difficult combination of two issues: it remains a challenge to distribute VPLs in a manner that simultaneously gives a high-quality indirect illumination solution for each frame, and to do so in a temporally coherent manner. We address both issues by building, and maintaining over time, an adaptive and temporally coherent distribution of VPLs in locations where they bring indirect light to the image. We introduce a novel heuristic sampling method that strives to only move as few of the VPLs between frames as possible. The result is, to the best of our knowledge, the first interactive global illumination algorithm that works in complex, highly-occluded scenes, suffers little from temporal flickering, supports moving cameras and light sources, and is output-sensitive in the sense that it places VPLs in locations that matter most to the final result.