Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are not stored in formats preserving semantic information is equally complex.

TreeV AE hierarchically divides samples according to their intrinsic characteristics, shedding light on hidden structures in the data.

Stereo matching aims to find horizontal pixel-wise displacement, i.e .disparity, between a rectified stereo image pair to recover depth for applications including autonomous driving, robotics, and augmented reality.

With noisy depth predictions as input, SDDR generates low-noise depth edge representations as pseudo-labels by coarse-to-fine self-distillation.