Corpus ID: 1216740

Depth Estimation Using Monocular and Stereo Cues

@inproceedings{Saxena2007DepthEU,
  title={Depth Estimation Using Monocular and Stereo Cues},
  author={Ashutosh Saxena and Jamie Schulte and A. Ng},
  booktitle={IJCAI},
  year={2007}
}
Depth estimation in computer vision and robotics is most commonly done via stereo vision (stereopsis), in which images from two cameras are used to triangulate and estimate distances. [...] Key Method In this paper, we apply a Markov Random Field (MRF) learning algorithm to capture some of these monocular cues, and incorporate them into a stereo system. We show that by adding monocular cues to stereo (triangulation) ones, we obtain significantly more accurate depth estimates than is possible using either…Expand
A new combination of monocular and stereo cues for dense disparity estimation
TLDR
A novel method combining monocular and stereo cues to compute dense disparities from a pair of images, which can generate a more accurate disparity map than existing methods from images with large textureless regions, e.g. snow, icebergs. Expand
Graph-based Stereo Matching by Incorporating Monocular Cues
Stereo vision is one of the most intensive and challenging problems in computer vision. It makes use of stereo cues to extract 3D information from 2D images. Besides stereo cues, there areExpand
Make3D: Depth Perception from a Single Still Image
TLDR
This paper presents algorithms for estimating depth from a single still image, and discusses applications of the depth perception algorithm in robotic navigation, in improving the performance of stereovision, and in creating large-scale 3-d models given only a small number of images. Expand
Combining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo
TLDR
This paper presents an algorithm for considering both stereo cues and structural priors to obtain a geometrically representative depth map from a narrow baseline stereo pair and shows through the results on stereo pairs of manmade structures captured outside of the lab that the algorithm exploits the advantages of both approaches to infer a better depth map of the scene. Expand
FloW vision: Depth image enhancement by combining stereo RGB-depth sensor
Human can recognize an object just by looking at the environment, this capability is very useful for designing the reference of humanoid robot with the ability of adapting it on its environment. ByExpand
Unsupervised Learning of Stereo Vision with Monocular Depth Cues
TLDR
Unsupervised learning of a stereo vision model involving monocular depth cues (shape from texture cues) and a conditional probability model defining the probability of the right image given the left is demonstrated. Expand
Depth estimation by combining stereo matching and coded aperture
TLDR
It is shown that with this system, it is possible to extract depth information robustly, by utilizing the inherent relation between the disparity and defocus cues, even for scene regions which are problematic for stereo matching. Expand
Combining Features and Semantics for Low-level Computer Vision
TLDR
This thesis proposes an efficient way of training a context network with a large receptive field size on top of a local network using dilated convolutions on patches and presents a method for learning context-aware features for solving optical flow using discrete optimization. Expand
3-D Reconstruction from Sparse Views using Monocular Vision
TLDR
This paper shows how monocular image cues can be combined with triangulation cues to build a photo-realistic model of a scene given only a few images-even ones taken from very different viewpoints or with little overlap. Expand
Unsupervised Depth Estimation From Monocular Images For Autonomous Vehicles
TLDR
This paper proposes DNN for depth estimation using unsupervised learning, then the proposed methods are evaluated using KITTI standard metrics which shows the promising way for self-driving cars. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Learning Depth from Single Monocular Images
TLDR
This work begins by collecting a training set of monocular images (of unstructured outdoor environments which include forests, trees, buildings, etc.) and their corresponding ground-truth depthmaps, and applies supervised learning to predict the depthmap as a function of the image. Expand
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
TLDR
This paper has designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. Expand
Maximum-likelihood depth-from-defocus for active vision
  • W. Klarquist, W. Geisler, A. Bovik
  • Computer Science
  • Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots
  • 1995
A new method for actively recovering depth information using image defocus is demonstrated and shown to support active stereo vision depth recovery by providing monocular depth estimates to guide theExpand
A Dynamic Bayesian Network Model for Autonomous 3D Reconstruction from a Single Indoor Image
  • E. Delage, Honglak Lee, A. Ng
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This paper presents a dynamic Bayesian network model capable of resolving some of the ambiguities of monocular vision and recovering 3d information for many images and shows that this model can be used for 3d reconstruction from a single image. Expand
Geometric context from a single image
TLDR
This work shows that it can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes, and provides a multiple-hypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label. Expand
Performance Analysis of Stereo, Vergence, and Focus as Depth Cues for Active Vision
TLDR
This paper compares the performances of the binocular cues of stereo and vergence, and the monocular cue of focus for range estimation using an active vision system and suggests ways to select a cue taking into account the computational and reliability aspects of the corresponding estimation process. Expand
High speed obstacle avoidance using monocular vision and reinforcement learning
TLDR
An approach in which supervised learning is first used to estimate depths from single monocular images, which is able to learn monocular vision cues that accurately estimate the relative depths of obstacles in a scene is presented. Expand
Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters
  • M. Tappen, W. Freeman
  • Mathematics, Computer Science
  • Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
TLDR
This work compares the belief propagation algorithm and the graph cuts algorithm on the same MRF's, which have been created for calculating stereo disparities, and finds that the labellings produced by the two algorithms are comparable. Expand
Shape from Shading: A Survey
TLDR
Six well-known SFS algorithms are implemented and compared, and the performance of the algorithms was analyzed on synthetic images using mean and standard deviation of depth error, mean of surface gradient error, and CPU timing. Expand
Bayesian modeling of uncertainty in low-level vision
  • R. Szeliski
  • Computer Science, Mathematics
  • International Journal of Computer Vision
  • 2004
TLDR
The uncertainty modeling techniques that are developed, and the utility of these techniques in various applications, support the claim that Bayesian modeling is a powerful and practical framework for low-level vision. Expand
...
1
2
3
...