Level Set Stereo For Cooperative Grouping With Occlusion

  title={Level Set Stereo For Cooperative Grouping With Occlusion},
  author={Jialiang Wang and Todd E. Zickler},
  journal={2021 IEEE International Conference on Image Processing (ICIP)},
Localizing stereo boundaries is difficult because matching cues are absent in the occluded regions that are adjacent to them. We introduce an energy and level-set optimizer that improves boundaries by encoding the essential geometry of occlusions: The spatial extent of an occlusion must equal the amplitude of the disparity jump that causes it. In a collection of figure-ground scenes from Middlebury and Falling Things stereo datasets, the model provides more accurate boundaries than previous… 
1 Citations

Figures and Tables from this paper

Level Set Binocular Stereo with Occlusions

An energy and level-set optimizer that improves boundaries by encoding occlusion geometry is introduced that applies to two-layer, figure-ground scenes, and it can be implemented cooperatively using messages that pass predominantly between parents and children in an undecimated hierarchy of multiscale image patches.



Hierarchical Deep Stereo Matching on High-Resolution Images

It is demonstrated that the performance-vs-speed tradeoff afforded by on-demand hierarchies may address sensing needs for time-critical applications such as autonomous driving.

A Bayesian approach to binocular steropsis

  • P. Belhumeur
  • Computer Science
    International Journal of Computer Vision
  • 2004
We develop a computational model for binocular stereopsis, attempting to explain the process by which the information detailing the 3-D geometry of object surfaces is encoded in a pair of stereo

On the Synergies between Machine Learning and Stereo: a Survey

Recent research in the field of learning-based depth estimation from images is reviewed highlighting the synergies, the successes achieved so far and the open challenges the community is going to face in the immediate future.

Local Detection of Stereo Occlusion Boundaries

The local detector for stereo occlusion boundaries is introduced based on a simple feedforward network with relatively small receptive fields and produces better boundaries than many other stereo methods, even without incorporating explicit stereo matching, top-down contextual cues, or single-image boundary cues.

Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation

We present a new dataset, called Falling Things (FAT), for advancing the state-of-the-art in object detection and 3D pose estimation in the context of robotics.1 By synthetically combining object

Stereo Processing by Semiglobal Matching and Mutual Information

  • H. Hirschmüller
  • Environmental Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 2008
This paper describes the Semi-Global Matching (SGM) stereo method, which uses a pixelwise, Mutual Information based matching cost for compensating radiometric differences of input images and demonstrates a tolerance against a wide range of radiometric transformations.

Toward Perceptually-Consistent Stereo: A Scanline Study

This work represents a disparity profile as a piecewise smooth function with explicit breakpoints between its smooth pieces, and shows this allows correlation and decorrelation to be integrated into an objective that requires only two types of local information: the correlation and its spatial gradient.

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

This work presents a method for extracting depth information from a rectified image pair by learning a similarity measure on small image patches using a convolutional neural network and examines two network architectures for this task: one tuned for speed, the other for accuracy.

Holistically-Nested Edge Detection

  • Saining XieZ. Tu
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
HED performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets, and automatically learns rich hierarchical representations that are important in order to resolve the challenging ambiguity in edge and object boundary detection.

Low-level vision by consensus in a spatial hierarchy of regions

A multi-scale framework for low-level vision, where the goal is estimating physical scene values from image data-such as depth from stereo image pairs-is introduced, which produces a distributional scene representation that is appropriate for combining with higher-level reasoning and other low- level cues.