Depth map processing with iterative joint multilateral filtering

Lai, PoLin; Tian, Dong; Lopez, Patrick

doi:10.1109/pcs.2010.5702589

Cited by 28 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome these problems, the joint bilateral filters (JBF) proposed [14][15][16] use color and spatial similarity between corresponding pixels in the image to enhance the depth map. Then, the iterative joint multilateral filtering (IJMF) suggested in [17] achieves the best unsharp masking structure through the training of parameters. This iterative method not only enhances the sharpness of the image but also smooths the corresponding video pixel values; however, it requires a complex training process to obtain the parameters.…”

Section: Introductionmentioning

confidence: 99%

Robust depth enhancement and optimization based on advanced multilateral filters

Chang

Chou

Yang

2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Stereo matching of two distanced cameras and structured-light RGB-D cameras are the two common ways to capture the depth map, which conveys the per-pixel depth information of the image. However, the results with mismatched and occluded pixels would not provide accurately well-matched depth and image information. The mismatched depth-image relations would degrade the performances of view syntheses seriously in modern-day three-dimension video applications. Therefore, how to effectively utilize the image and depth to enhance themselves becomes more and more important. In this paper, we propose an advanced multilateral filter (AMF), which refers spatial, range, depth, and credibility information to achieve their enhancements. The AMF enhancements could sharpen the image, suppress noisy depth, filling depth holes, and sharpen the depth edges simultaneously. Experimental results demonstrate that the proposed method provides a superior performance, especially around the object boundary.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust depth enhancement and optimization based on advanced multilateral filters

Chang

Chou

Yang

2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Due to this inherent problem of Kinect, several authors have proposed different approaches to filter the depth data to get high accuracy depth map where the color image taken from the RGB camera of the Kinect has exact point to point correspondence with the depth image. The most common way to suppress the distortion is to use traditional filtering techniques like bilateral filter or Kalman filter [13], [14]. Though these filters reduce the distortion, the edges of the depth map become blurred.…”

Section: Introductionmentioning

confidence: 99%

“…Though these filters reduce the distortion, the edges of the depth map become blurred. Lai et al proposed a method to filter the depth map using the corresponding RGB information of the scene [14] but the algorithm largely depends on the camera calibration and performs poorly for larger depth. In this paper, we use a depth video and its corresponding color video to measure a high accuracy depth map of the scene.…”

Section: Introductionmentioning

confidence: 99%

Depth filtering using total variation based video decomposition

Bhattacharya

Venkatesh

Gupta

2015

2015 Third International Conference on Image Information Processing (ICIIP)

View full text Add to dashboard Cite

In vision based applications, depth plays a crucial role from different aspects. From 3D rendering to automation, precision in depth measurement is important for acceptable performances. Though several techniques have been proposed to capture depth map of a scene, the estimation is either erroneous or much expensive for regular usage. Thus, the demand for high accuracy depth measurement is prominent in the field of robotics and computer vision.In this paper, we propose a method to estimate high accuracy depth map from a raw depth map for both static and dynamic scenes. This depth filtering is done by exploiting the spatio.temporal information present in a depth video and by taking the color information of the scene into account.

show abstract

“…There are many variants of it named joint bilateral filter or joint multilateral filter which are proposed to 'correct' the depth maps. These variants are better aligned with the corresponding edges in the video frames, but do not 'preserve' the edges in the depth maps [4,5]. Although the performances of them are remarkable, there are some inevitable drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Integration of Joint Multilateral Filter and Projective Transformation For Depth Map Enhancement

Zuo¹,

Li²,

Zhou³

et al. 2014

2014 International Conference on Automatic Control Theory and Application

View full text Add to dashboard Cite

Abstract-Although many depth map enhancement algorithms based on joint multilateral filter have been developed, they still have some drawbacks. Firstly, the edges of video and depth can be similar but not the same. Some texture of video will appear in where should not be in depth when the joint multilateral filter is used to enhance the depth. Secondly, it is difficult to trade off the window size and shape for reliable result and rate of convergence. Thirdly, these filters will lead to fuzzy result. In this paper, integration of joint multilateral filter and projective transformation is proposed to partially overcome the difficulties above. Based on the theory of multiple view geometry, the correspondences of projection points are determined by projective transformation in two camera image planes when the real scene is modeled as a plane. The proposed method over-segments the image into many small pieces. In each segment, the transformation matrix is calculated firstly if the segment is sufficient small and the reliable pixels determined by cross-check are enough. Then the matrix is checked to determine whether the segment can be approximated as a planar surface or not. The unreliable pixels in depth will be refined using reliable matrices in the corresponding segments. The rest unreliable pixels are refined by using joint multilateral filter. Experimental results show that the proposed algorithm can achieve a performance better than that with joint multilateral filter only.

show abstract

Depth map processing with iterative joint multilateral filtering

Cited by 28 publications

References 7 publications

Robust depth enhancement and optimization based on advanced multilateral filters

Robust depth enhancement and optimization based on advanced multilateral filters

Depth filtering using total variation based video decomposition

Integration of Joint Multilateral Filter and Projective Transformation For Depth Map Enhancement

Contact Info

Product

Resources

About