Stereo video
1 / 44

Stereo Video - PowerPoint PPT Presentation

  • Uploaded on

Stereo Video. Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid Temporally Consistent Disparity and Optical Flow via Efficient Spatio-temporal Filtering

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Stereo Video' - ruby

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Stereo video

Stereo Video

Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos

Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid

Temporally Consistent Disparity and Optical Flow via Efficient Spatio-temporal Filtering

Efficient Spatio-temporal Local Stereo Matching Using Information Permeability Filtering

A temporally consistent disparity maps from uncalibrated stereo videos

A. Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos

Michael Bleyer and Margrit Gelautz

International Symposium on Image and Signal Processing and Analysis (ISPA) 2009

B real time spatiotemporal stereo matching using the dual cross bilateral grid

B. Real-time Spatiotemporal Stereo Matching Using The Dual-cross-bilateral Grid

Christian Richardt, Douglas Orr, Ian Davies, Antonio Criminisi, and Neil A. Dodgson1

The European Conference on Computer Vision (ECCV) 2010

C temporally consistent disparity and optical flow via efficient spatio temporal filtering

C. Temporally Consistent Disparity And Optical Flow Via Efficient Spatio-temporal Filtering

Asmaa Hosni, Christoph Rhemann,

Michael Bleyer, and Margrit Gelautz

The Pacific-Rim Symposium on Image and Video Technology (PSIVT) 2011

D efficient spatio temporal local stereo matching using information permeability filtering

D. Efficient Spatio-temporal Local Stereo Matching Using Information Permeability Filtering

Cuong Cao Pham, Vinh Dinh Nguyen, and Jae Wook Jeon

 International Conference on Image Processing



  • Introduction

  • Related Works

  • Methods and Results

    • A. Median Filter

    • B. Temporal DCB Grid

    • C. Spatial-temporal Weighted Smoothing

    • D. Three-pass Aggregation

  • Comparison

  • Conclusion


  • Stereo matching issues only focus on static image pairs.

  • The conventional methods estimate the disparities by using spatial and color information.

  • The important problem of extending to video is flickering.

  • Solution :

    • Base on local methods (for real-time)

    • Enforce temporally consistent (for flickering)

Related works1
Related Works

  • About Local Methods

    • The key of local method lies in the cost aggregation step.

    • Aggregate the cost data from the neighboring pixels within a finite size window.

    • The most well-known method is edge-preserving algorithm.

      • Adaptive support wight

      • Geodesic Diffusion 

      • Bilateral filter

      • Guided filter

Related works2
Related Works

  • Single-frame stereo matching

Related works3
Related Works

  • Spatio-temporal stereo matching

    • The inter disparity difference between two successive frames is minimized to enforce the temporal consistency.

A median filter2
A. Median filter

  • Computing 1 disparity map takes 1 second.

  • But a video content about 30~60 frames per second.

    • => Can NOT achieve real-time.

  • No data and comparison.

B temporal dcb grid
B. Temporal DCB Grid

  • Bilateral Grid

    • It runs faster and uses less memory as σ increases.

  • Dual-Cross-Bilateral Grid

B temporal dcb grid1
B. Temporal DCB Grid

  • Dichromatic DCB Grid

  • Comparison(fps)


B temporal dcb grid2
B. Temporal DCB Grid

  • Temporal DCB Grid

    • Last n = 5 frames, each weighted by wi

    • i=0 : current frame

    • i=1 : previous frame


B temporal dcb grid3
B. Temporal DCB Grid



Stereo video

B. Temporal DCB Grid

Source data

B temporal dcb grid4
B. Temporal DCB Grid

  • Onlyuseintensityinformation

  • Justnear-real-time

C spatial temporal weighted smoothing
C. Spatial-temporal Weighted Smoothing

  • Cost initialization

    • Construct a spatio-temporal cost volume for each disparity d.

  • Cost aggregation

    • Smooth cost volume with a spatio-temporal filter.(Guided filter [1])

  • Disparity computation

    • Select the lowest costs as disparity(WTA)

  • Refinement

    • Wighted median filter

[1]Rhemann, C., Hosni, A., Bleyer, M., Rother, C., Gelautz, M.

Fast Cost-Volume Filtering for Visual Correspondence and Beyond.

CVPR(2011) and PAMI (2013)

C spatial temporal weighted smoothing2
C. Spatial-temporal Weighted Smoothing

  • Cost initialization

  • Cost aggregation

wk: wx * wy* wt

: smoothness parameter

C spatial temporal weighted smoothing3
C. Spatial-temporal Weighted Smoothing

  • The guided filter weights can be implemented by a sequence of linear operations.

  • All summations are 3D box filters and can be computed in O(N)time.

C spatial temporal weighted smoothing4
C. Spatial-temporal Weighted Smoothing

  • Disparity computation : Winner take all

  • Refinement : Wighted Meadian filter

    => Just adjust to reduce single frame error.

C spatial temporal weighted smoothing5
C. Spatial-temporal Weighted Smoothing

  • Temporal vs. frame-by-frame processing.

    • 2nd row: Disparity maps computed by a frame-by-frame implementation show flickering artifacts.

    • 3rd row: Our proposed method exploits temporal information, thus can remove most artifacts

D three pass cost aggregation
D. Three-pass cost aggregation

  • Three-pass cost aggregation technique based on information permeability(Adaptive Support-Weight).[2]

[2] Yoon, K.J., Kweon, I.S.: Locally Adaptive Support-Weight Approach for Visual

Correspondence Search. In: CVPR (2005)

D three pass cost aggregation1
D. Three-pass cost aggregation

Frame i+1

Frame i

Frame i-1

D three pass cost aggregation2
D. Three-pass cost aggregation

Show the effectiveness of using temporal information in addition to spatial information .

  • Matching cost initialization

    • v = (x, y, t) represents the spatial and temporal positions of a voxel.

  • Similarity(weighted) function

D three pass cost aggregation3
D. Three-pass cost aggregation

  • Spatial Aggregation : Horizontal and then Vertical

D three pass cost aggregation4
D. Three-pass cost aggregation

  • Temporal Aggregation : Forward and backward

  • Disparity computation : WTA

  • Refinement

    • consistency check

    • 3 × 3 median filter.

D three pass cost aggregation5
D. Three-pass cost aggregation

  • Computational Complexity

    • Only sixmultiplications and nine additions per voxel

    • It is still more efficient than the adaptive support-weight approach.

  • Withoutmotionestimation



Includepost-processing:consistency checkand 3 × 3 median filter


  • Based on edge-preserving methods.

  • Extend these concepts to time dimension.

  • These methods only solved slow motion scenes.

  • They do not perform well with dynamic scenes that contain large object motions.