2011 IEEE International Conference on Consumer Electronics (ICCE) 2011
DOI: 10.1109/icce.2011.5722787
|View full text |Cite
|
Sign up to set email alerts
|

Improved depth map filtering for 3D-TV systems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 5 publications
0
4
0
Order By: Relevance
“…Next, the proposed method aligns I C and I D . For image alignment, existing methods [15, 16] use joint bilateral filter [17], whereas the proposed method uses depth‐adaptive joint bilateral filter [16] that considers depth discontinuity. This helps stable alignment when an area has depth discontinuity and no significant gradient edges in I C .…”
Section: Proposed Segmentation Methods Using Colour and Depth Imagesmentioning
confidence: 99%
“…Next, the proposed method aligns I C and I D . For image alignment, existing methods [15, 16] use joint bilateral filter [17], whereas the proposed method uses depth‐adaptive joint bilateral filter [16] that considers depth discontinuity. This helps stable alignment when an area has depth discontinuity and no significant gradient edges in I C .…”
Section: Proposed Segmentation Methods Using Colour and Depth Imagesmentioning
confidence: 99%
“…Based on the BF [90], which is one of the most popular local filtering methods, Silva et al [145] propose an adaptive JBF, whereby the depth map is guided by the corresponding texture view sequence for eliminating the compression artefacts. Similar to [145], Liu et al [146, 147] propose a TF by using the depth map and the corresponding colour view image in the range domain of the filter to improve the quality of depth maps and mitigate the compression artefacts. All of these mentioned methods are colour‐guided pixel‐based methods.…”
Section: Depth Map Artefacts Reductionmentioning
confidence: 99%
“…The resulting graph for the selected model obtained from the curve-fitting process is depicted in Figure 5. matching (HRM) [31] based depth map; (b) segment tree (ST) [32] based depth map; (c) rapid semi global matching (RSGM) [33] based depth map; (d) RSGM with joint bilateral filter (RSGM_FIL) [34,35] based depth map.…”
Section: Dec Measurement-based No-reference Quality Evaluation Modelmentioning
confidence: 99%