Watson, J; Firman, M; Brostow, G; Turmukhambetov, D; (2020) Self-supervised monocular depth hints. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). (pp. pp. 2162-2171). The Institute of Electrical and Electronics Engineers (IEEE)

Preview

Text 1909.09051.pdf - Accepted Version Download (2MB) | Preview

Abstract

Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser-scans or other ground-truth data. The disadvantage, however, is that the photometric reprojection losses used with self-supervised learning typically have multiple local minima. These plausible-looking alternatives to ground-truth can restrict what a regression network learns, causing it to predict depth maps of limited quality. As one prominent example, depth discontinuities around thin structures are often incorrectly estimated by current state-of-the-art methods. Here, we study the problem of ambiguous reprojections in depth-prediction from stereo-based self-supervision, and introduce Depth Hints to alleviate their effects. Depth Hints are complementary depth-suggestions obtained from simple off-the-shelf stereo algorithms. These hints enhance an existing photometric loss function, and are used to guide a network to learn better weights. They require no additional data, and are assumed to be right only sometimes. We show that using our Depth Hints gives a substantial boost when training several leading self-supervised-from-stereo models, not just our own. Further, combined with other good practices, we produce state-of-the-art depth predictions on the KITTI benchmark.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item