In this work, we proposed a novel depth adaptive tone mapping scheme for stereo HDR imaging and 3D display. The scheme employed a new depth-adaptive cross-trilateral filter (DA-CTF) for recovering High Dynamic Range (HDR) images from multiple Low Dynamic Range (LDR) images captured at different exposure levels. Explicitly leveraging additional depth information in the tone mapping operation correctly identify global contrast change and detail visibility change by preserving the edges and reducing halo artifacts in the synthesized 3D views by depth-image-based rendering (DIBR) procedure. The experiments show that the proposed DA-CTF and DIBR scheme outperforms state-of-the-art operators in the enhanced depiction of tone mapped HDR stereo images on LDR displays.
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
A Novel Approach for Multi-view 3D HDR Content Generation via Depth Adaptive Cross Trilateral Tone Mapping
1. A NOVEL APPROACH FOR MULTI-VIEW 3D HDR CONTENT GENERATION
VIA DEPTH ADAPTIVE CROSS TRILATERAL TONE MAPPING
Mansi Sharma1
, M. S. Venkatesh2
, Gowtham Ragavan3
, Rohan Lal4
Indian Institute of Technology Madras1,3,4
Indian Institute of Technology Delhi2
Wednesday, 11 December 2019
2. Multi-view High Dynamic Range Imaging
● Offer HDR Depth-contrast and Stereo Personalization in 3D Display
Technologies
● Multi-user and Personalized HDR Stereo 3D Display Applications
● Increased Realism and “3D-ness”
- depth-from-HDR effect reproducible in LDR conditions
● Scene parameterization
- MPEG standardized multi-view video-plus-depth & DIBR
- Future proofed for existing and emerging 3D multi-view video formats
- Compatible with 2D TV, stereoscopic, multi-view, or eye-tracking displays
4. Main Contributions
● A novel depth-image-based rendering scheme for multi-view 3D HDR content
generation.
● A new HDR tone mapping operator based on depth-adaptive cross-trilateral filter.
- Recover 3D HDR images from multiple LDR images captured at different exposure levels
- Explicitly leverage additional depth information in the tone mapping operation
- Tone mapping process for the realistic display of 3D HDR images
- Preserve detail visibility changes
- Preserve edges and reduce halo artifacts in the synthesized LDR 3D views
9. Comparison of Extracted Base Layer
Bilateral Filtering
Frédo Durand and Julie Dorsey. 2002. Fast bilateral filtering for the display of
high-dynamic-range images. ACM Trans. Graph. 21, 3 (July 2002), 257-266.
14. Comparison of Proposed Tone Mapping
Frédo Durand and Julie Dorsey. 2002. Fast bilateral filtering for the display of
high-dynamic-range images. ACM Trans. Graph. 21, 3 (July 2002), 257-266.
PROPOSED
Durand
& Julie Halo Artifacts
Reduced
15. Comparison of Rendered 3D HDR Content
Frédo Durand and Julie Dorsey. 2002. Fast bilateral filtering for the display of
high-dynamic-range images. ACM Trans. Graph. 21, 3 (July 2002), 257-266.
Durand
& Julie
18. No Reference Quality Assessment
Kundu et al. No-Reference Quality Assessment of Tone-Mapped HDR Pictures. in IEEE TIP,
26(6), pp. 2957-2971, 2017.
19. Conclusion
● First-of-its-kind Scheme
- Makes use of MVD with 3D HDR content creation
● End-to-end rendering pipeline
- New depth-adaptive tone mapping operator
● Design a display-invariant 3D TV HDR content production pipeline
● Future Work
- Glossy, reflective, reflection materials
- Issue of saturated regions in one camera
- Effects of specular highlights following normal stereoscopic geometry
20. Applications
● Stereoscopic 3DTV/VR HMDs
● Parallax Barrier/Lenticular based 3D Displays
● Multi-view 3D Displays
● Light Field HDR Tone Mapping