Jin Xin
Professor

Professional Experience & Education

Prof. Jin received the M.S. degree in communication and information system and the Ph.D. degree in information and communication engineering, both from Huazhong University of Science and Technology, Wuhan, China, in 2002 and 2005, respectively.

From 2004 to 2005, she was an Intern with the Internet Multimedia Group, Microsoft Research Asia, Beijing, China. From 2006 to 2008, she was a Postdoctoral Fellow with The Chinese University of Hong Kong. From 2008 to 2012, she was a Visiting Lecturer with the Information Technology Research Organization, Waseda University, Fukouoka, Japan. Since Mar. 2012, she has been with the Graduate School at Shenzhen, Tsinghua University, China, where she is currently a Professor in the Division of Information Science & Technology. Her current research interests include computational photography, power-constrained multimedia signal processing. She has published over 120 conference and journal papers.

Dr. Jin is an IEEE Senior Member, and a member of SPIE and ACM. She is the chair of 3D video compression standard group of the Audio Video Standard Workgroup of China (AVS). She received Youth Top-notch Talent of Guangdong Special Support Program in 2017, the second prize of National Science and Technology Progress Award in 2016, the first prize of Guangdong science and technology award in 2015, and ISOCC Best Paper Award in 2010. She has served on many conference committees, e.g., PCM, VCIP, etc. and served as a reviewer for many transactions, e.g., IEEE TIP, TCSVT, etc. and international conferences, e.g., ICIP, ISCAS, ICME, etc.


Research

Prof. Jin's research interests include computational photography and power constrained multimedia signal processing. Traditional cameras integrate light over the dimensions, such as directions, colors, temporal variations, by converting photons into electrons. The process preserves a subset of two dimensional, or some three-dimensional-time- varying information, while loses a huge amount of information in other plenoptic dimensions, e.g. directions of light rays, wavelength and polarizations.

Computational photography tries to make a big breakthrough in fundamental imaging theory and techniques to record the volumetric and contextual light field. In imaging theory, we research on theoretical imaging modeling and wave propagation analysis to improve the fidelity in recording the light field. Based on the theoretical researches, novel light field imaging systems are designed and built to reconstruction the light field with compact optical structure. Power constrained multimedia signal processing tries to process the high-dimensional light field information to realize novel applications like imaging through scattering media, light field stitching, depth estimation, refocusing, light field compression and light field rendering. During processing, not only the processing quality but also the implementation complexity is considered simultaneously to make the approaches be friendly to real applications.

Past & Current Projects:

  • Jan. 2019 – Dec. 2023, 2nd contributor,NSFC National Major Scientific Research Instrument Project (61827804): Coded photography instrument in scattering scene.

  • Jan. 2018 – Dec. 2021,Principal Investigator,NSFC Project (61771275): Research on enhancement and modeling for plenoptic acquisition.

  • Apr. 2018 – Dec. 2021,Principal Investigator,Shenzhen Key project of Fundamental Research: Research on key technology of light field detection based on plenoptic cameras.

  • June 2017 – May 2020,Principal Investigator,Youth Top-notch Talent of Guangdong Special Support Program.

  • July 2017 – July, 2019,2nd contributor,Foundation of Science and Technology Department of Sichuan Province (2017JZ0032c): Research on VR video compression techniques for next generation video coding standards.

  • July 2017 – June 2020, Principal Investigator,Shenzhen Fundamental Research Project: Hybrid coding architecture compatible Intra prediction methods for plenoptic images.

  • Jan. 2015 – Dec. 2017, Principal Investigator,863 Project: Light field based real 3D video acquisition and generation.

  • Jan. 2015 – Jan. 2018, Principal Investigator,NSF of Guandong Province: Ultra low power super-high-definition video coding and power-rate-distortion optimization.

  • Dec. 2014 – Dec. 2016, Principal Investigator,Shenzhen Project: Ultra low power super-high-definition video coding, power-rate-distortion optimization and systems.

  • Sept. 2014 - Sept. 2016, Principal Investigator,Shenzhen Key Lab Project: Efficient representation, structural analysis and reconstruction for computational imaging.

  • Jan. 2014 – Dec. 2017,Principal Investigator,NSFC Project (61371138): Research on Mobile Cloud Computing based Free-viewpoint Synthesis, Adaptive Offloading and Power Optimization,”.

  • Jan. 2013 – Dec. 2016,Principal Investigator of subproject,NSFC-Guangdong Joint Foundation Key Project: Sparse Representation, Structured Processing, and Joint Coding of Multidimentional Visual Space.


Selected Publications:

2018

  • Xin Jin, Zhouping Wang, Xiaoyu Wang, Qionghai Dai, “Depth of field extended scattering imaging by light field estimation,” Optics Letters, vol. 43, no. 20, pp. 4871-4874, Oct. 2018.

  • Xin Jin, Li Liu and Qionghai Dai, “Approximation and Blind Reconstruction of Volumetric Light Field,” Optics Express, vol. 26, no. 13, pp. 16836-16852, June 2018.

  • Zhouping Wang, Xin Jin and Qionghai Dai, “Non-invasive imaging through strongly scattering media based on speckle pattern estimation and deconvolution,” Scientific Reports, 8, article number 9088(2018), 2018.

  • Xin Jin, Haixu Han and Qionghai Dai, “Plenoptic Image Coding using Macropixel-based Intra Prediction,” IEEE Trans. Image Process., vol. 27, no. 8, pp. 3954 – 3968, 2018.

  • Xin Jin, Zhanqi Liu, Qian Li and Qionghai Dai, “Depth Assisted Adaptive Workload Balancing for Parallel View Synthesis,” IEEE Trans. Multimedia, 2018.

  • Junke Li, Xin Jin, Yanqin Chen, Qionghai Dai, “Enhanced depth estimation for light field cameras by variable-patch-size tensor extraction,” ISPACS2018, Ishigaki Island, Okinawa, Japan, Nov. 27 - 30, 2018.

  • Chuanpu Li, Xin Jin, Yanqin Chen and Qionghai Dai, “Storage-computational Complexity Efficient Light Field Reconstruction,” IEEE Intl. Conf. Digital Signal Processing, Shanghai, China, Nov. 19-21, 2018.

  • Lingjun Li, Xin Jin, Haixun Han, Qionghai Dai, “Macropixel based Fast Motion Estimation for Plenoptic Video Compression,” Pacific-Rim Conference on Multimedia (PCM), Hefei, China, Sept. 21-22, 2018. LNCS 11166, pp. 730–739, 2018.

  • Heng Zhang, Xin Jin, Qionghai Dai, “Synthetic aperture based on plenoptic camera for seeing through occlusions,” PCM2018, Hefei, China, Sept. 21-22, 2018. LNCS 11164, pp. 158–167, 2018.

  • Haixu Han, Xin Jin, Qionghai Dai, “Plenoptic image compression via simplified subaperture projection,” PCM2018, Hefei, China, Sept. 21-22, 2018. LNCS 11165, pp. 274–284, 2018.

  • Zhouping Wang, Xin Jin & Qionghai Dai, "Superresolution imaging through scattering media by spectrum correlation", SPIE Photonics Asia, Beijing, China, Oct. 11-13, 2018.

  • Pei Wang, Xin Jin, Chuanpu Li, Yanqin Chen, Qionghai Dai, “Light Field Stitching for Parallax Tolerance,” IEEE Intl. Conf. Image Process. (ICIP), Athens, Greece, Oct. 7-10, 2018, pp. 2585-2589.

  • Yanqin Chen, Xin Jin, Qionghai Dai, "Defocused image formation model for plenoptic imaging," OSA Imaging and Applied Optics Congress: Computational Optical Sensing and Imaging, Orlando, Florida, United States, June 15-28, 2018.

  • Yanqin Chen, Xin Jin, Li Liu and Qionghai Dai, “High-speed light field image formation analysis using wavefield modeling with flexible sampling,” IEEE Intl. Conf. Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, Apr. 15-20, 2018, pp. 6523-6527.

2017

  • Xin Jin, Haixu Han and Qionghai Dai, “Image Reshaping for Efficient Compression of Plenoptic Content,” IEEE Journal of Selected Topics in Signal Processing, vol. 11, no. 7, pp. 1173-1186, 2017.

  • Xin Jin, Li Liu and Qionghai Dai, “Point spread function and depth-invariant focal sweep point spread function for plenoptic camera 2.0,” Optics Express, vol. 25, no. 9, pp. 9947-9962, May 2017.

  • Yanqin Chen, Xin Jin and Qionghai Dai, “Distance measurement based on light field geometry and ray tracing,” Optics Express, vol. 25, no. 1, pp. 59-76, Jan. 2017.

  • Liang Yuan, Xin Jin, Yangguang Li, Chun Yuan, “Depth Map Super-resolution Via Low-resolution Depth Guided Joint Trilateral Up-sampling,” Journal of Visual Communication and Image Representation, 46(2017): 280-291.

  • H. Wang, I. Katsavounidis, J. Zhou, J. Park, S. Lei, M. O. Pun, Xin Jin, R. Wang, X. Wang, Y. Zhang, J. Huang, S. Kwong, C.-C. Jay Kuo, “A Large-Scale Compressed Video Quality Dataset Based on JND Measurement”, Journal of Visual Communication and Image Representation, 46(2017): 292-302.

  • Li Liu, Xin Jin and Qionghai Dai, “Image Formation Analysis and Light Field Information Reconstruction for Plenoptic Camera 2.0,” Pacific-Rim Conference on Multimedia (PCM) 2017, Sept. 28-29, Harbin, China.

  • Haixu Han, Xin Jin and Qionghai Dai, “Lenslet image compression using adaptive micropixel prediction,” IEEE Int’l. Conf. on Image Proc. (ICIP), Beijing, China, Sept. 17-20, 2017.

  • Yanqin Chen, Xin Jin and Qionghai Dai, “Distance estimation based on light field geometric modeling,” ICME2017 Workshop: Hot3D, Hong Kong, July 10-14, 2017, pp. 43-48.

  • Haixu Han, Xin Jin and Qionghai Dai, “Lenslet image compression based on image reshaping and macro-pixel intra prediction,” International Conf. on Multimedia & Expo (ICME), Hong Kong, July 10-14, 2017, pp. 1177-1182.

  • Qian Li, Xin Jin, Zhanqi Liu and Qionghai Dai, “Dynamic cloud offloading for view synthesis,” IEEE Intl. Conf. Acoustics, Speech and Signal Processing (ICASSP), New Orleans, USA, Mar. 5-9, 2017, pp. 2951-2955.

  • Yanwen Qin, Xin Jin and Qionghai Dai, “Enhanced depth estimation for hand-held light field cameras,” IEEE Intl. Conf. Acoustics, Speech and Signal Processing (ICASSP), New Orleans, USA, Mar. 5-9, 2017, pp. 2032-2036.

2016

  • Xin Jin and Qionghai Dai, “Clustering Based Content Adaptive Tiles under On-chip Memory Constraints,” IEEE Trans. Multimedia, vol. 18, no. 12, pp. 2331-2344, 2016.

  • Xin Jin, Yatong Xu and Qionghai Dai, “Depth Dithering based on Texture Edge-assisted Classification,” Signal Processing: Image Communication, vol.47, pp. 56-71, 2016.

  • Haixu Han, Xin Jin and Qionghai Dai, “Plenoptic Image Compression Based on Linear Transformation and Interpolation,” Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) 2016, Dec. 13-16, 2016, Jeju, Korea.

  • Yu Zhang, Xin Jin and Qionghai Dai, “A 3D Subjective Quality Prediction Model Based On Depth Distortion,” VCIP2016, Nov. 27-30, Chengdu, China.

  • Yifu Hu, Xin Jin and Qionghai Dai, “Efficient Imaging through Scattering Media by Random Sampling,” MMSP2016, Sept. 21-23, 2016, Canada.

  • Leye Wei, Xin Jin, Zhiyong Wu and Lei Zhang, “A Real-time Gesture-based Unmanned Aerial Vehicle Control System,” PCM2016, Sept. 15-16, Xi’an, China.

  • Yiqi Jiang, Xin Jin and Zhiyong Wu, “Robust Video Inpainting Based on Joint Gradient and Noise Minimization,” PCM2016, Sept. 15-16, Xi’an, China.

  • Liang Yuan, Xin Jin and Chun Yuan, “Enhanced Joint Trilateral Up-sampling for Super-Resolution,” PCM2016, Sept. 15-16, Xi’an, China.

  • Yifu Hu, Xin Jin, Kaiyu Wei and Qionghai Dai, “Imaging through scattering media with intensity modulated incoherent sources,” IEEE Int’l. Conf. on Image Proc. (ICIP), Phoenix, USA, Sept. 25-28, 2016.

  • Yu Zhang, Xin Jin and Qionghai Dai, “A SVR Based Quality Metric for Depth Quality Assessment,” IEEE ISCAS, Montreal, Canada, May 22-25, 2016, pp. 2567-2570.

  • Yatong Xu, Xin Jin and Qionghai Dai, “Depth Fused from Intensity Range and Blur Estimation for Light-field Cameras,” IEEE ICASSP, Shanghai, China, Mar. 20-25, 2016, pp. 2857-2861.

2015

  • Xin Jin, Zhuoying Zeng, Satoshi Goto and Qionghai Dai, “A fast encoder of frame-compatible format based on content similarity for 3D distribution,” Signal Processing: Image Communication, vol. 35, pp. 20-34, July, 2015.

  • Kaiyun Wei, Xin Jin, Yifu Hu and Qionghai Dai, “Non-invasive imaging based on sparse representation,” International Workshop on Multimedia Signal Processing (MMSP), Xiamen, China, Oct. 19-21, 2015.

  • Zhanqi Liu, Xin Jin and Qionghai Dai, “Motion and Depth Assisted Workload Prediction for Parallel View Synthesis,” Pacific-Rim Conference on Multimedia (PCM), Korea, Sept. 16-19, 2015.

  • Yatong Xu, Xin Jin and Qionghai Dai, “Depth Estimation by analyzing intensity distribution for light-field cameras, ” International Conf. on Image Process. (ICIP), Quebec city, Canada, Sept. 27-30, 2015.

  • Zhanqi Liu, Xin Jin, Chenyang Li and Qionghai Dai, “A Workload Balanced Parallel View Synthesis for FTV,” 40th IEEE Intl. Conf. Acoustics, Speech and Signal Processing (ICASSP) 2015, Apr. 19-24, 2015, Brisbane, Australia, pp. 1558-1562.

2014

  • Guangsheng Chi, Xin Jin and Qionghai Dai, “A Fast Coding Algorithm Based on Inter-View Correlations for 3D-HEVC,” IEEE Visual Communications and Image Processing (VCIP) Dec. 7-10, 2014, pp.374-377.

  • Chenyang Li, Xin Jin and Qionghai Dai, “A novel distortion model for depth coding in 3D-HEVC,” ICIP, Paris, France, Oct. 27-30, 2014, pp.3228-3232.

  • Yatong Xu, Xin Jin and Qionghai Dai, “Spatial-temporal Depth De-noising for Kinect based on Texture Edge-assisted Depth Classification,” International Conf. on Digital Signal Processing (19th DSP), Hong Kong, Aug. 20-23, 2014, pp.327-332.

  • Guangsheng Chi, Xin Jin and Qionghai Dai, “A quad-tree and statistics based fast CU depth decision algorithm for 3D-HEVC,” International Conf. on Multimedia & Expo (ICME): HoT3D Workshop, Chengdu, China, July 14-18, 2014, pp.1-5.


Oct. 2017, Young Teacher Teaching Award of Tsinghua University of year 2017

Apr. 2017, Youth Top-notch Talent of Guangdong Special Support Program

Dec. 2016, The second prize of National Science and Technology Progress Award

Feb. 2016, The first prize of Guangdong science and technology award

Sept. 2011, Waseda University IT Research Organization Encouragement Award

Nov. 2010, IEEE SSCS Seoul Chapter Award for "Low Power Parallel Encoding System for Video Surveillance Applications", 2010 International SoC Design Conference

Mar. 2006, Best Ph. D. dissertation award of HUST of year 2006

June 2002, Excellent graduate student of Batch 2002 of HUST

June 1999, Excellent graduate of Batch 1999 of HUST