Comparing some recent stereo algorithms in the wild

Tons of progress has been made to estimate depth from a pair of stereo images. The current state-of-the-art methods all rely on deep learning to reach impressive accuracy levels on public benchmarks, even on hard textureless areas. But how do they actually perform in practice on stereo images captured in the wild? I am especially interested in indoor scenes (room scanning, object scanning), while the most frequently used large stereo benchmark is KITTI, which is focused on outdoor autonomous driving. So let’s see how well they generalize and what the performance/memory tradeoffs are for some of them.

Using deep learning to undo line anti-aliasing

Line anti-aliasing makes color segmentation difficult on images that include thin lines or small markers, for example in plots. Undoing it would allow software tools for the colorblind to more easily highlight regions that share the same color in color charts. Since it’s relatively easy to generate ground truth data, let’s see if we can tackle this problem with deep learning.