Depth Estimation Using Monocular and Stereo Cues

By Ashutosh Saxena, Jamieson Schulte, Andrew Y. Ng. 2007

290 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning a Multi-View Stereo Machine (2017, background): “Approaches which predict shape from a single image have been proposed in form of direct depth map regression [46, 31, 10], generating multiple depth maps from novel viewpoints [51], producing voxel occupancies [5, 16], geometry images [49] and point clouds [11].”
Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs (2015, background): “[9, 16] tackles the problem with a multi-scale Markov Random Field (MRF) model, with the parameters of the model learned through supervised learning.”
A multirange architecture for collision‐free off‐road robot navigation (2009, background): “• DOI: 10.1002/rob.20270 Chris Crudele and Urs Miller Net-Scale Technologies Morganville, New Jersey 07751 Yann LeCun Courant Institute of Mathematical Sciences New York University New York, New York 10003 Received 7 April 2008; accepted 10 October 2008 We present a multilayered mapping, planning, a”
Make3D: Learning 3D Scene Structure from a Single Still Image (2009, methodology): “Examples include stereovision [4], [22], image segmentati on [10], and object classification [24].”
Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras (2019, background): “Historically much research has been devoted to it, including a large bodies of research on stereo, multi-view geometry, and active sensing [29, 21, 9].”
Autonomous MAV flight in indoor environments using single image perspective cues (2011, background): “Such an approach requires high camera resolution and often constructs incomplete models of the environment [3], [32].”
Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models (2012, background): “…several approaches have tried to combine these different classifiers for related tasks in vision [1], [2], [3], [4], [5], [6], [7], [8], [9], [10]; however, most of them tend to be ad hoc (i.e., a hard-coded rule is used) and often an intimate knowledge of the inner workings of the…”
Who killed the directed model? (2008, unknown): “These have been successfully learnt as priors for natural images [13] [22] [23], stereo depth [16] [15], single image depth [14], object segmentation [2], optical flow [12], intrinsic images [20], etc.”
Learning 3-D Scene Structure from a Single Still Image (2007, background): “However, their depthmaps, although useful for tasks such as a robot driving [12] or improving performance of stereovision [15], were not accurate enough to produce visually-pleasing 3-d fly-throughs.”
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models (2010, methodology): “manually designed the terms in an MRF to combine depth estimation with object detection [2] and stereo cues [10].”
Are we ready for autonomous driving? The KITTI vision benchmark suite (2012, unknown): “To obtain a high stereo and optical ﬂow ground truth density, we register a set of consecutive frames (5 before and 5 after the frame of interest) using ICP.”
Continuous Markov Random Fields for Robust Stereo Estimation (2012, background): “The constraints on label combinations at junctions often force the labeling of the entire line drawing [14].”
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth (2021, background): “Some works fuse conventional matching-based stereo estimation with monocular depth cues [71, 60, 17].”
3-D Depth Reconstruction from a Single Still Image (2007, methodology): “7cm. [25] We collected a total of 425 image+depthmap pairs, with an image resolution of 1704x2272 and a depthmap resolution of 86x107.”
Displets: Resolving stereo ambiguities using object knowledge (2015, background): “While the mutual benefits of recognition and reconstruction have been shown using simple priors and multiple views [15,29], little work has addressed the binocular stereo problem in this context with notable exceptions [33,48,61].”
Monocular vision SLAM for indoor aerial vehicles (2009, unknown): “In sensing, efforts to retrieve depth information from a still image by using machine learning such as the Markov Random Field learning algorithm [6, 7] are shown to be effective.”