Fast and Robust Multiple ColorChecker Detection using Deep Convolutional Neural Networks

Of course it’s not all fluid simulations, high-resolution generative models, and real-time mocap. Sometimes you just need a good solution to a simple problem. ColorCheckers are reference standards that professional photographers and filmmakers use to ensure predictable results under every lighting condition. The objective of this work is to propose a new fast and robust…Read More

Peeking Behind Objects: Layered Depth Prediction from a Single Image

Here’s a nice approach to depth estimation which combines in-painting to allow simulation of slight camera moves from just a single image. While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of…Read More

Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a latent representation that encodes skeletal joint positions, and at the same time learns a deep representation of volumetric body…Read More

Deep Generative Modeling for Scene Synthesis via Hybrid Representations

A recent post demonstrated a data-driven system for indoor scene synthesis. This work is motivated by similar but is noteworthy not only for its results – which allows for repeated inclusion of a given type of object and interpolation of entire scenes – but also the rigorous analysis of their approach which is bound to…Read More

Deep Learning Advances on Different 3D Data Representations: A Survey

Much of the attention surrounding deep learning and its impact on visual effects has focused on image-based techniques, in particular the compelling examples produced by denoising, segmentation, and generative adversarial models. Research continues, however, into application of machine learning to 3D data – meshes, point clouds, voxel grids, and so on – and how to…Read More

Temporally Coherent Video Harmonization Using Adversarial Networks

A over B plus magic equals…..? Compositing is one of the most important editing operations for images and videos. The process of improving the realism of composite results is often called harmonization. Previous approaches for harmonization mainly focus on images. In this work, we take one step further to attack the problem of video harmonization….Read More

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

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