Temporal consistency enhancement on depth sequences

Fu, Deliang; Zhao, Yin; Yu, Lu

doi:10.1109/pcs.2010.5702503

Cited by 19 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This causes depth errors and hence reduces the depth accuracy. Fu et al [14] and Kim et al [20] only partially solve this problem by filtering stationary image areas only. However, our test sequences have both camera and object motion and hence both approaches will not work.…”

Section: Quantitative Resultsmentioning

confidence: 99%

“…3.2, we describe three methods for temporal propagation. Alternatively, Fu et al [14] propose a 3-tap recursive temporal filter to filter stationary image areas only. First they compute the structural similarity (SSIM) between pixel p in the color images of the current frame n and pixel p in frame n À 1 and n À 2: Then the output depth at pixel p in the previous frame is multiplied by a weight, which is computed from the per pixel SSIM, and averaged with the depth at pixel p in the current frame.…”

Section: Depth Upsamplingmentioning

confidence: 99%

“…We construct each method's parameter vector h as the concatenation of all parameters that belong to said method, 14 hence each element of h Real scene, no camera motion, independent object motion All test sequences are resampled with interpolation factor I r and decimation factor D r and cropped by C L ; C R ; C T ; C B , i.e., the number of pixels by which the left right, top and bottom image border are cropped, respectively Note that C R and C B are large enough to remove the border effect of the polyphase filters that occurs on the right and bottom image borders, respectively represents a parameter, and each parameter can only take values from the ranges specified in Table 5.…”

Section: Parameter Space Analysismentioning

confidence: 99%

See 2 more Smart Citations

Overview of efficient high-quality state-of-the-art depth enhancement methods by thorough design space exploration

Vosters

Varekamp²,

Haan

2015

J Real-Time Image Proc

View full text Add to dashboard Cite

Section: Quantitative Resultsmentioning

confidence: 99%

Section: Depth Upsamplingmentioning

confidence: 99%

Section: Parameter Space Analysismentioning

confidence: 99%

See 1 more Smart Citation

Overview of efficient high-quality state-of-the-art depth enhancement methods by thorough design space exploration

Vosters

Varekamp²,

Haan

2015

J Real-Time Image Proc

View full text Add to dashboard Cite

“…Depth image preprocessing, the first step, improves the quality of the rendered image by reducing the number of holes [32][33][34]. When the viewpoint is moved by the DIBR, an area where no pixel information exists is generated.…”

Section: Dibr Processmentioning

confidence: 99%

Robust Template-Based Watermarking for DIBR 3D Images

et al. 2018

View full text Add to dashboard Cite

Several depth image-based rendering (DIBR) watermarking methods have been proposed, but they have various drawbacks, such as non-blindness, low imperceptibility and vulnerability to signal or geometric distortion. This paper proposes a template-based DIBR watermarking method that overcomes the drawbacks of previous methods. The proposed method exploits two properties to resist DIBR attacks: the pixel is only moved horizontally by DIBR, and the smaller block is not distorted by DIBR. The one-dimensional (1D) discrete cosine transform (DCT) and curvelet domains are adopted to utilize these two properties. A template is inserted in the curvelet domain to restore the synchronization error caused by geometric distortion. A watermark is inserted in the 1D DCT domain to insert and detect a message from the DIBR image. Experimental results of the proposed method show high imperceptibility and robustness to various attacks, such as signal and geometric distortions. The proposed method is also robust to DIBR distortion and DIBR configuration adjustment, such as depth image preprocessing and baseline distance adjustment.

show abstract

“…Fig. 2(b) also presents results of 1D depth sequences of proposed method as well as two referenced methods: temporal median filtering with depth hole filling (t-MedFilter), and temporal consistency enhancement (TC-Enhance) proposed by Fu [13], where our method can efficiently smooth the noisy and flickering depth sequences, while the rest are sensitive to outliers and cannot find the static structure of input signals.…”

Section: Static Scene Analysismentioning

confidence: 99%

Temporal depth video enhancement based on intrinsic static structure

Sheng

Ngan

2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Depth video enhancement is an essential preprocessing step for various 3D applications. Despite extensive studies of spatial enhancement, effective temporal enhancement that both strengthens temporal consistency and keeps correct depth variation needs further research. In this paper, we propose a novel method to enhance the depth video by blending raw depth frame with the estimated intrinsic static structure, which defines static structure of captured scene and is estimated iteratively by a probabilistic generative model with sequentially incoming depth frames. Our experimental results show that the proposed method is effective both in static and dynamic scene and is compatible with various kinds of depth videos. We will demonstrate that superior performance can be achieved in comparison with existing temporal enhancement approaches.Index Terms-depth video enhancement, temporal enhancement, probabilistic model, variational approximation

show abstract

Temporal consistency enhancement on depth sequences

Cited by 19 publications

References 7 publications

Overview of efficient high-quality state-of-the-art depth enhancement methods by thorough design space exploration

Overview of efficient high-quality state-of-the-art depth enhancement methods by thorough design space exploration

Robust Template-Based Watermarking for DIBR 3D Images

Temporal depth video enhancement based on intrinsic static structure

Contact Info

Product

Resources

About