Related papers: Unsupervised Learning of 3D Scene Flow from Monocu…
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…
3D reconstruction from a single 2D image was extensively covered in the literature but relies on depth supervision at training time, which limits its applicability. To relax the dependence to depth we propose SceneRF, a self-supervised…
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…
We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including…
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…
Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…
Understanding visual reality involves acquiring common-sense knowledge about countless regularities in the visual world, e.g., how illumination alters the appearance of objects in a scene, and how motion changes their apparent spatial…
This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often…
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…
Recently neural scene representations have provided very impressive results for representing 3D scenes visually, however, their study and progress have mainly been limited to visualization of virtual models in computer graphics or scene…
We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions. Our key…
We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in…
Scene flow is a description of real world motion in 3D that contains more information than optical flow. Because of its complexity there exists no applicable variant for real-time scene flow estimation in an automotive or commercial vehicle…
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…
Scene flow describes the 3D position as well as the 3D motion of each pixel in an image. Such algorithms are the basis for many state-of-the-art autonomous or automated driving functions. For verification and training large amounts of…
Inaccurate optical flow estimates in and near occluded regions, and out-of-boundary regions are two of the current significant limitations of optical flow estimation algorithms. Recent state-of-the-art optical flow estimation algorithms are…
Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general…
Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene…
Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based…