# The Edge of Depth: Explicit Constraints between Segmentation and Depth Source: [The Edge of Depth: Explicit Constraints between Segmentation and Depth]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:11:14.110Z Authors: Shengjie Zhu, Garrick Brazil, Xiaoming Liu Published: 2020-04-01T00:03:20.000Z ## Abstract 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, constraints 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 advances the state of the art on unsupervised monocular depth estimation in the KITTI. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Monocular Depth Estimation on KITTI (Eigen)](): Monocular Depth Estimation; KITTI (Eigen); Abs Rel: 0.091. - [Depth Estimation on NYU v2 (test)](): Depth Estimation; NYU v2 (test); Threshold Accuracy (delta \< 1.25): 56.3. ## Original sources and implementation [Original paper]() [PDF]()