Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods.Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

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 selfsupervised 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. We demonstrate that our selective training using DepthHints is a general enhancement that can improve multiple leading self-supervised training algorithms, allowing our implementations to reach better minima. The Depth Hints can come from the same stereo image data, via, e.g. OpenCV's stereo estimates [13,14].3. We show that our selective training with Depth Hints, coupled with sensible network design choices, leads us to outperform most other algorithms. We achieve state-of-the-art results on the KITTI dataset [8], outperforming both our baseline model and previously published results.

Building a complete 3D model of a scene, given only a single depth image, is underconstrained. To gain a full volumetric model, one needs either multiple views, or a single view together with a library of unambiguous 3D models that will fit the shape of each individual object in the scene. We hypothesize that objects of dissimilar semantic classes often share similar 3D shape components, enabling a limited dataset to model the shape of a wide range of objects, and hence estimate their hidden geometry. Exploring this hypothesis, we propose an algorithm that can complete the unobserved geometry of tabletop-sized objects, based on a supervised model trained on already available volumetric elements. Our model maps from a local observation in a single depth image to an estimate of the surface shape in the surrounding neighborhood. We validate our approach both qualitatively and quantitatively on a range of indoor object collections and challenging real scenes.

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also available at test time. The vast majority of monocular networks do not make use of this extra signal, thus ignoring valuable information that could be used to improve the predicted depth. Those that do, either use computationally expensive test-time refinement techniques or off-theshelf recurrent networks, which only indirectly make use of the geometric information that is inherently available.We propose ManyDepth, an adaptive approach to dense depth estimation that can make use of sequence information at test time, when it is available. Taking inspiration from multi-view stereo, we propose a deep end-to-end cost volume based approach that is trained using self-supervision only. We present a novel consistency loss that encourages the network to ignore the cost volume when it is deemed unreliable, e.g. in the case of moving objects, and an augmentation scheme to cope with static cameras. Our detailed experiments on both KITTI and Cityscapes show that we outperform all published self-supervised baselines, including those that use single or multiple frames at test time.

No abstract