Neural rendering algorithms introduce a fundamentally new approach for photorealistic rendering, typically by learning a neural representation of illumination on large numbers of ground truth images. When training for a given variable scene, i.e., changing objects, materials, lights and viewpoint, the space \(\mathcal {D} \)  of possible training data instances quickly becomes unmanageable as the dimensions of variable parameters increase. We introduce a novel Active Exploration method using Markov Chain Monte Carlo, which explores \(\mathcal {D} \)  , generating samples (i.e., ground truth renderings) that best help training and interleaves training and on-the-fly sample data generation. We introduce a self-tuning sample reuse strategy to minimize the expensive step of rendering training samples. We apply our approach on a neural generator that learns to render novel scene instances given an explicit parameterization of the scene configuration. Our results show that Active Exploration trains our network much more efficiently than uniformly sampling, and together with our resolution enhancement approach, achieves better quality than uniform sampling at convergence. Our method allows interactive rendering of hard light transport paths (e.g., complex caustics) – that require very high samples counts to be captured – and provides dynamic scene navigation and manipulation, after training for 5-18 hours depending on required quality and variations.

Equal-time comparisons (2 minutes). Our method reduces noise compared to Müller et al. [MGN17], by efficiently guiding paths based on the product of the BSDF and incoming radiance at each path vertex. We show Mean Absolute Error (MAE).

Neural Radiance Fields (NeRFs) have revolutionized novel view synthesis for captured scenes, with recent methods allowing interactive free-viewpoint navigation and fast training for scene reconstruction. However, the implicit representations used by these methods---often including neural networks and complex encodings---make them difficult to edit. Some initial methods have been proposed, but they suffer from limited editing capabilities and/or from a lack of interactivity, and are thus unsuitable for interactive editing of captured scenes. We tackle both limitations and introduce NeRFshop, a novel end-to-end method that allows users to interactively select and deform objects through cage-based transformations. NeRFshop provides fine scribble-based user control for the selection of regions or objects to edit, semi-automatic cage creation, and interactive volumetric manipulation of scene content thanks to our GPU-friendly two-level interpolation scheme. Further, we introduce a preliminary approach that reduces potential resulting artifacts of these transformations with a volumetric membrane interpolation technique inspired by Poisson image editing and provide a process that "distills" the edits into a standalone NeRF representation.