HDR image reconstruction from a single exposure using deep CNNs

After creating LDR images by applying simulated camera sensor saturation to real HDR photos, the authors trained a model which could perform the inverse LDR->HDR operation and also generalize to previously unseen images. What’s more, they have released their dataset which can be downloaded from their project page. Camera sensors can only capture a limited…Read More

Machine Learning Labs

Machine learning in practice can be an arduous task. Managing multiple iterations of code, processing input data, feature engineering, training models, visualizing and tabulating results, performing analysis, and using experience to draw conclusions and adapt the system in a way which might yield improved results. In many cases you feel like you have more promising…Read More

Interactive Example-Based Terrain Authoring with Conditional Generative Adversarial Networks

This is a really great example of not only how data-driven tools of the future might help enhance the creative process but also of how a machine learning problem can be broken down into smaller sub-models in order to aid interactivity and provide greater control. Authoring virtual terrains presents a challenge and there is a…Read More

Learning to Predict Indoor Illumination from a Single Image

Here are some superb results with clear implications for lighting workflows. What’s more, The authors intend to release their data set – some 1750 high resolution HDR environment maps – soon. “We propose an automatic method to infer high dynamic range illumina- tion from a single, limited eld-of-view, low dynamic range photograph of an indoor…Read More

Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation

Depth map and UV map from a single image! “It has been recently shown that neural networks can recover the geometric structure of a face from a single given image. A common denominator of most existing face geometry reconstruction methods is the restriction of the solution space to some low-dimensional subspace. While such a model…Read More