Depth map upsampling with a confidence-based joint guided filter

Yang, Yoonmo; Lee, Hean Sung; Oh, Byung Tae

doi:10.1016/j.image.2019.05.014

Cited by 5 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Separating results x and y can be achieved by iteratively computing x k and y k according to formula (5)- (7). Finally, we note that the separation algorithm not only is a preprocessing step to suppress the noise in the acquired LR depth image, but also is a post-processing step to remove artifacts produced by our upsampling method.…”

Section: A Structure and Noise Separationmentioning

confidence: 99%

“…Jiang et al [6] propose a deep edge map guided depth SR method which includes an edge prediction subnetwork and an SR subnetwork. Yang et al [7] use depth-texture similarity to construct a pixel-level confidence calculation method for 3D view synthesis, and construct a joint guided filter based on confidence, which not only considered the smoothness between depth pixels, but also incorporated depth-texture similarity, improving the performance of sampling on depth images and the quality of synthesized views. Lei et al [8] propose a view synthesis quality based trilateral depth-map upsampling method, which considers depth smoothness, texture similarity and view synthesis quality in the upsampling filter.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Upsampling Based Depth Image Super-Resolution Reconstruction

Zhou

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Constrained by current sensing technology, depth camera only acquires a low-resolution depth image that does not meet actual requirements. To solve this problem, this paper take a divide-and-conquer strategy to synthesize a high-resolution depth image from a low-resolution range image under the guidance of a registered high-resolution color image. Initially, the depth image is divided into planar areas and edge regions. For different zones, we exploit different methods to interpolate the missing depths. At planar area, the linear interpolation method is employed to perform upsampling. At edge region, a segmentation-separation upsampling method is used to interpolate the missing values. Then the upsampling result are refined on the Depth CNN that is built in this paper. We conduct extensive experiments on the benchmark database and real world data with various upsampling rates to illustrate the upsampling ability of our method. The comparison with classical super-resolution algorithms demonstrates that our upsampling algorithm achieves the best quality with fewer artifacts and our depth CNN outperforms the most state-of-the-art methods in terms of qualitative and quantitative evaluations.

show abstract

Section: A Structure and Noise Separationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improved Upsampling Based Depth Image Super-Resolution Reconstruction

Zhou

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It is analysed that the larger resolution feature maps are more processed in the fusion network. [32], EGF [12], CJGF [40], DJF [21], PAC [36], DBPN [9], DKN [17], Ours, and ground-truth (from left to right).…”

Section: F Complexity Comparisonmentioning

confidence: 99%

“…We consider that the given image is distorted by blurring, and it was simply modeled via Gaussian blurring with σ b . As shown in Table 7, the blurred FIGURE 5: Visual comparisons for the 8× upsampled Middlebury and NYU v2 depth maps by various methods: BF [32], EGF [12], CJGF [40], DJF [21], PAC [36], DBPN [9], DKN [17], Ours, and ground-truth (from left to right).…”

Section: G Noisy Environment Evaluationmentioning

confidence: 99%

“…This filter employs an onion peel-like filtering, which significantly improves the performance of the filter. As an extension of EGF, Yang et al proposed a confidence-based joint guided filter (CJGF) by controlling the filtering order using the confidence map derived from the shape of the unreliable region, depth map, and color pixel values [40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling

Yang

Kim

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Depth maps play an important role in the representation of 3D information. They are often simultaneously acquired with color images; however, their resolution is significantly lower than that of color images owing to hardware limitations. In this paper, we propose a novel approach to upsample depth maps by using geometric deformation instead of pixel value refinement, which is employed in a majority of existing methods. This approach, known as grid warping, displaces the position of blurred pixels around the edge towards the center of the edge. The displacement vector for warping is obtained from an analysis of the corresponding high-resolution color image. Furthermore, we propose an edge signal and displacement vector modeling for a more effective analysis. The experimental results show that the proposed method significantly improves the quantitative and visual performance, as compared to state-of-the-art methods. The source codes of the proposed method will be available at https://github.com/yym064/DeepGridWarp.

show abstract

Learning content-aware feature fusion for guided depth map super-resolution

Zuo,

Wang,

et al. 2024

Signal Processing: Image Communication

View full text Add to dashboard Cite

Depth map upsampling with a confidence-based joint guided filter

Cited by 5 publications

References 15 publications

Improved Upsampling Based Depth Image Super-Resolution Reconstruction

Improved Upsampling Based Depth Image Super-Resolution Reconstruction

Deep Convolutional Grid Warping Network for Joint Depth Map Upsampling

Learning content-aware feature fusion for guided depth map super-resolution

Contact Info

Product

Resources

About