Geodesy

Benchmark (surveying)

Neuroscience

Biology

Contrast (vision)

Constraint (computer-aided design)

Computer science

Geology

Image segmentation

Segmentation

Pattern recognition (psychology)

Mathematics

Geography

Enhanced Data Rates for GSM Evolution

Depth perception

Artificial intelligence

Geometry

Ground truth

Monocular

Perception

Consistency (knowledge bases)

Computer vision

In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraint from semantic segmentation has been explored implicitly such as sharing and transforming features. In contrast, we propose to explicitly measure the border consistency between segmentation and depth and minimize it in a greedy manner by iteratively supervising the network towards a locally optimal solution. Partially this is motivated by our observation that semantic segmentation even trained with limited ground truth (200 images of KITTI) can offer more accurate border than that of any (monocular or stereo) image-based depth estimation. Through extensive experiments, our proposed approach advance the state of the art on unsupervised monocular depth estimation in the KITTI benchmark.

The Edge of Depth: Explicit Constraints Between Segmentation and Depth