A Rich Stereoscopic 3D High Dynamic Range Image &amp; Video Database of Natural Scenes

Wadaskar, Aditya; Sharma, Mansi; Lal, Rohan

doi:10.1109/ic3d48390.2019.8975903

Cited by 3 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed scheme is tested on HDR stereoscopic image datasets [44], [45]. Stereo multi-exposure images/videos have been captured in [44] employing ZED 3D camera. The 3D HDR image dataset created by Aditya et al [44] covers natural scenes.…”

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

“…Stereo multi-exposure images/videos have been captured in [44] employing ZED 3D camera. The 3D HDR image dataset created by Aditya et al [44] covers natural scenes. The scenes feature rich biodiversity of the Indian Institute of Technology Madras campus.…”

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

“…However, captured multi-exposure images/videos of natural scenes contain slight to medium, partially traceable motion of objects. Readers refer to the publication for more details about the characteristics of the datasets [44]. Some stereo multi-exposure images used in the experiments are shown in Fig.…”

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

Sharma,

Wadaskar

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Display technology must offer high dynamic range (HDR) contrast-based depth induction and 3D personalization simultaneously. Efficient algorithms to compress HDR stereo data is critical. Direct capturing of HDR content is complicated due to the high expense and scarcity of HDR cameras. The HDR 3D images could be generated in low-cost by fusing low-dynamicrange (LDR) images acquired using a stereo camera with various exposure settings. In this paper, an efficient scheme for coding multi-exposure stereo images is proposed based on a tensor low-rank approximation scheme. The multi-exposure fusion can be realized to generate HDR stereo output at the decoder for increased realism and exaggerated binocular 3D depth cues.For exploiting spatial redundancy/sparsity in LDR stereo images, the stack of multi-exposure stereo images is decomposed into a set of projection matrices and a core tensor following an alternating least squares Tucker decomposition model. The compact, low-rank representation of the scene, thus, generated is further processed by 3D extension of High Efficiency Video Coding standard. The encoding with 3D-HEVC enhance the proposed scheme efficiency by exploiting intra-frame, inter-view and the inter-component redundancies in low-rank approximated representation. We consider constant luminance property of IPT and Y C b Cr color space to precisely approximate intensity prediction and perceptually minimize the encoding distortion. Besides, the proposed scheme gives flexibility to adjust the bitrate of tensor latent components by changing the rank of core tensor and its quantization. Extensive experiments on natural scenes demonstrate that the proposed scheme outperforms state-of-theart JPEG-XT and 3D-HEVC range coding standards.

show abstract

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

Sharma,

Wadaskar

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The performance of proposed architecture is evaluated on three different data sets: Middlebury [17], [37], [38], Scene flow [30], and multi-exposure natural scene stereo datasets [41].…”

Section: A Datasetmentioning

confidence: 99%

“…Our proposed model's performance is also evaluated on natural complex scenes. We use diverse stereoscopic 3D multiexposure images database [41], captured within the beautiful campus of Indian Institute of Technology Madras, India. The campus is a protected forest area, carved out of Guindy National Park.…”

Section: A Datasetmentioning

confidence: 99%

MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications

Choudhary¹,

Sharma²,

V³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Display technologies have evolved over the years. It is critical to develop practical HDR capturing, processing, and display solutions to bring 3D technologies to the next level. Depth estimation of multi-exposure stereo image sequences is an essential task in the development of cost-effective 3D HDR video content. In this paper, we develop a novel deep architecture for multi-exposure stereo depth estimation. The proposed architecture has two novel components. First, the stereo matching technique used in traditional stereo depth estimation is revamped. For the stereo depth estimation component of our architecture, a mono-to-stereo transfer learning approach is deployed. The proposed formulation circumvents the cost volume construction requirement, which is replaced by a ResNet based dual-encoder single-decoder CNN with different weights for feature fusion. EfficientNet based blocks are used to learn the disparity. Secondly, we combine disparity maps obtained from the stereo images at different exposure levels using a robust disparity feature fusion approach. The disparity maps obtained at different exposures are merged using weight maps calculated for different quality measures. The final predicted disparity map obtained is more robust and retains best features that preserve the depth discontinuities. The proposed CNN offers flexibility to train using standard dynamic range stereo data or with multi-exposure low dynamic range stereo sequences. In terms of performance, the proposed model surpasses state-of-the-art monocular and stereo depth estimation methods, both quantitatively and qualitatively, on challenging Scene flow and differently exposed Middlebury stereo datasets. The architecture performs exceedingly well on complex natural scenes, demonstrating its usefulness for diverse 3D HDR applications.

show abstract

MEStereo-Du2CNN: a dual-channel CNN for learning robust depth estimates from multi-exposure stereo images for HDR 3D applications

et al. 2023

View full text Add to dashboard Cite

A Rich Stereoscopic 3D High Dynamic Range Image & Video Database of Natural Scenes

Cited by 3 publications

References 20 publications

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications

MEStereo-Du2CNN: a dual-channel CNN for learning robust depth estimates from multi-exposure stereo images for HDR 3D applications

Contact Info

Product

Resources

About