Neural Importance Sampling

Here’s an early exploration into using neural networks for guiding Monte Carlo integration, from Disney Research. Interestingly, they note how their learned models can be adapted to slightly modified scenes (e.g. changes in camera) and that might make it quite applicable to optimizing renders of animations. We propose to use deep neural networks for generating…Read More

Joint Learning of Intrinsic Images and Semantic Segmentation

We’ve previously covered both semantic segmentation and intrinsic image decomposition. Here we see a novel proposal to combine the two tasks under the premise that knowledge of one can assist the other. Models and datasets are coming soon. Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known…Read More


SIGGRAPH 2018 is just around the corner. Starting on Sunday August 12th in Vancouver, British Columbia and ending Thursday August 16th it’s looking like this is going to be a bumper year for presentations which cover applications of deep learning and demonstrate some truly stunning results. The full schedule is here, yet you can see…Read More

Texture Mixing by Interpolating Deep Statistics via Gaussian Models

Here’s an interesting technique which may provide new ways in which to generate and synthesize textures from examples via interpolation and style transfer. Recently, enthusiastic studies have devoted to texture synthesis using deep neural networks, because these networks excel at handling complex patterns in images. In these models, second-order statistics, such as Gram matrix, are…Read More

GRAINS: Generative Recursive Autoencoders for INdoor Scenes

Rule-based systems for procedural generation of complex environments such as interiors, cities, and landscapes have been around for a while. Here is a novel data-driven approach to not only learn how objects interact with each other in order to be able to produce new arrangements but also perform conversion of 2D floor plans to 3D…Read More