SIGGRAPH ASIA 2014 Technical Paper Fast Forward Digital Photography.

SIGGRAPH ASIA 2014Technical Paper Fast Forward

Digital Photography

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits

FlexISP: A Flexible Camera Image Processing Framework

• Author– Felix Heide (UBC), – Markus Steinberger

(TU Graz), – Yun-Ta Tsai (NVIDIA), – Mushfiqur Rouf (UBC), – Dawid Pająk (NVIDIA), – Dikpal Reddy (NVIDIA), – Orazio Gallo (NVIDIA),

– Jing Liu (UC Santa Cruz), – Wolfgang Heidrich

(KAUST), – Karen Egiazarian (TUT), – Jan Kautz (NVIDIA), – Kari Pulli (NVIDIA)

https://research.nvidia.com/publication/flexisp-flexible-camera-image-processing-framework

FlexISP: A Flexible Camera Image Processing Framework

• Abstract

FlexISP: A Flexible Camera Image Processing Framework

• Abstract

FlexISP: A Flexible Camera Image Processing Framework

• Abstract

FlexISP: A Flexible Camera Image Processing Framework

• Videohttps://www.youtube.com/watch?v=DvEAtE_bn9Q

FlexISP: A Flexible Camera Image Processing Framework

• ConclusionFlexISP, a framework and a system that replaces the traditional image processing pipeline. The image formation model is expressed as a single objective function, which is solved using a proximal operator framework.

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits

Fast Burst Images Denoising

• Author– Ziwei Liu (The Chinese University of Hong Kong)– Lu Yuan (Microsoft Research)– Xiaoou Tang (The Chinese University of Hong Kong)– Matt Uyttendaele (Microsoft Research Technologies)– Jian Sun (Microsoft Research)

http://personal.ie.cuhk.edu.hk/~lz013/projects/BurstDenoising.html

Fast Burst Images Denoising

• Abstract– a fast denoising method that produces a clean image

from a burst of noisy images.

Fast Burst Images Denoising

• Videohttps://www.youtube.com/watch?v=HjG4zecx2dw

Fast Burst Images Denoising

• Limitations

Fast Burst Images Denoising

• Conclusion– a fast denoising method that produces a clean image

from a burst of noisy images.

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits

Spatial-spectral Encoded Compressive Hyperspectral Imaging

• Author– Xing Lin (Tsinghua University)– Yebin Liu (Tsinghua University)– Jiamin Wu (Tsinghua University)– Qionghai Dai (Tsinghua University)

Beijing Key Laboratory of Multi-dimension &Multi-scale Computational Photography (MMCP), Tsinghua University

http://media.au.tsinghua.edu.cn/XingLin/SSCSI/sscsi.jsp

Spatial-spectral Encoded Compressive Hyperspectral Imaging

• Abstract

Spatial-spectral Encoded Compressive Hyperspectral Imaging

• Video (dead now)– http://

media.au.tsinghua.edu.cn/XingLin/SSCSI/sscsivideo.avi

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

Spatial-spectral Encoded Compressive Hyperspectral Imaging

• Summary

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits

Mirror Mirror: Crowdsourcing Better Portraits

• Author– Jun-Yan Zhu (University of California, Berkeley)– Aseem Agarwala (Adobe)– Alexei A. Efros (University of California, Berkeley)– Eli Shechtman (Adobe)– Jue Wang (Adobe)

http://www.eecs.berkeley.edu/~junyanz/projects/mirrormirror/

Mirror Mirror: Crowdsourcing Better Portraits

• Abstract

Mirror Mirror: Crowdsourcing Better Portraits

Mirror Mirror: Crowdsourcing Better Portraits

Mirror Mirror: Crowdsourcing Better Portraits

Mirror Mirror: Crowdsourcing Better Portraits

• Video– https://www.youtube.com/watch?v=AWjcAbvtm04

Mirror Mirror: Crowdsourcing Better Portraits

• Conclusion

Digital Photography

• FlexISP: A Flexible Camera Image Processing

Framework

• Fast Burst Images Denoising

• Spatial-spectral Encoded Compressive

Hyperspectral Imaging

• Mirror Mirror: Crowdsourcing Better Portraits