Feng Yang is a Senior Staff Software Engineer at Google Research, where he leads the AIM Engine team. He was a postdoctoral researcher at Illumination&Imaging Lab, Robotics Institute, CMU, supervised by Prof. Srinivasa Narasimhan. He interned at Intel Research Center, Beijing advised by Eric Li and Nokia Research, Palo Alto, CA advised by Kari Pulli. He was a Research Assistant with the Broadband Network and Digital Multimedia Laboratory, Tsinghua University, advised by Prof. Qionghai Dai, member of Chinese Academy of Engineering and Audiovisual Communications Laboratory, EPFL, advised by Prof. Martin Vetterli, President of EPFL and member the US National Academy of Engineering. His research interests include deep learning, image quality assessment, digital rights management, image and video synthesis, image and video processing, computational photography, video streaming, distributed video coding, sampling theories, and mobile sensing.

Most recently, he is working on building the next generation image/video processing, serving and storage system with AI. A lot of his algorithms are landed in Google's products and significantly increased the company's revenue and reduced cost. 

Feng Yang received the B.Eng. and M.Eng. degrees in automatic control from Tsinghua University, Beijing, China, in 2004 and 2007, respectively. He won Outstanding master thesis of Tsinghua University. He got Ph.D. degree in communication systems at the École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland in 2012. He won Fritz Kutter Award for best PhD thesis. He holds several patents and some of them sold to Rambus Inc. 

Academic Service: 

Publications

F. Yang, M. Vetterli and L. Sbaiz (Dirs.). Bits from Photons: Oversampled Binary Image Acquisition (Fritz Kutter award for best PhD thesis), EPFL, Lausanne, 2012. (Slides for PhD defense)

[7] I. Oguz, J. Ke, Q. Wang, F. Yang, M. Yildirim, N. U. Dinc, J.-L. Hsieh, C. Moser, D. Psaltis, Forward-Forward Training of an Optical Neural Network, Optics Letters, vol. 48, issue 20, pp. 5249-5252, 2023.

[6] X. Luo, Y. Li, H. Chang, C. Liu, P. Milanfar, F. Yang, DVMark: a deep multiscale framework for video watermarking, IEEE Trans. on Image Processing, 2023.

[5] J. Ke, T. Zhang, Y. Wang, P. Milanfar, F. Yang, MRET: Multi-resolution transformer for video quality assessment, Front. Signal Process., 2023.

[4] H. Talebi, D. Kelly, X. Luo, I. G. Dorado, F. Yang, P. Milanfar, and M. Elad, Better Compression With Deep Pre-Editing,  IEEE Trans. on Image Processing, vol. 30, pp. 6673-6685, 2021.

[3] F. Yang and J. Suo, Light field: theory, acquisition and applications.  Communications of China Computer Federation, vol. 8, no. 8, pp. 13-19, 2012 (In Chinese).

[2] F. Yang, Y.M. Lu, L. Sbaiz and M. Vetterli, Bits from Photons: Oversampled Image Acquisition Using Binary Poisson Statistics ,  IEEE   Trans. on Image Processing , vol. 21, issue 4, pp. 1421-1436, 2012.

[1] G. Ding, F. Yang, Q. Dai, and W. Xu. A distributed source coding theorem based region of interest image compression method.  IEE Electronics Letters, vol. 41, no. 22, pp. 1215-1217, Oct. 2005.

[39] S. H. Lee, S. Kim, I. Yoo, F. Yang, D. Cho, Y. Kim, H. Chang, J. Kim, S. Kim, Soundini: Sound-Guided Diffusion for Natural Video Editing, arXiv 2023.

[38] Urvang Joshi; Yue Chen; Innfarn Yoo; Shan Li; Feng Yang; Debargha Mukherjee, Switchable CNNs for in-loop restoration and super-resolution for AV2, Proc. SPIE 12674, Applications of Digital Image Processing XLVI, 2023.

[37] L. Han, Y. Li, H. Zhang, P. Milanfar, D. Metaxas, F. Yang, Svdiff: Compact parameter space for diffusion fine-tuning, ICCV 2023.

[36] Junjie Ke, Keren Ye, Jiahui Yu, Yonghui Wu, Peyman Milanfar, Feng Yang, VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining, CVPR 2023.

[35] Xiyang Luo, Michael Goebel, Elnaz Barshan, Feng Yang, LECA: A learned approach for efficient cover-agnostic watermarking, EI 2023.

[34] A. Lahiri, J. Ke, D. Vlasic, X. Yao, T. Yu, F. Yang, Identifying Document Images with Glare Using Global and Localized Feature Fusion, ICIP 2022.

[33] Y. Wang, J. G. Yim, N. Birkbeck, J. Ke, H. Talebi, X. Chen, F. Yang, B. Adsumilli, Revisiting the efficiency of UGC video quality assessment, ICIP 2022.

[32] Z. Tu, H. Talebi, H. Zhang, F. Yang, P. Milanfar, A. Bovik, and Y. Li, MaxViT: Multi-Axis Vision Transformer, ECCV 2022.

[31] I. Yoo, H. Chang, X. Luo, O. Stava, C. Liu, P. Milanfar, F. Yang, Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings, CVPR 2022.

[30] Z. Tu, H. Talebi, H. Zhang, F. Yang, P. Milanfar, A. Bovik, and Y. Li, MAXIM: Multi-Axis MLP for Image Processing, CVPR 2022, Oral, Best paper finalist.

[29] J. Ke, Q. Wang, Y. Wang, P. Milanfar, and F. Yang, MUSIQ: Multi-scale Image Quality Transformer, ICCV 2021.

[28] Y. Li, P. Jin, F. Yang, C. Liu, M.-H. Yang, and P. Milanfar, COMISR: Compression-Informed Video Super-Resolution, ICCV 2021, Oral.

[27] J. C. Mier, E. Huang, H. Talebi, F. Yang, and P. Milanfar, Deep Perceptual Image Quality Assessment For Compression, ICIP 2021. 

[26] X. Fan, Q. Wang, J. Ke, F. Yang, B. Gong, and M. Zhou, Adversarially Adaptive Normalization for Single Domain Generalization, CVPR 2021.

[25] Y. Wang, J. Ke, H. Talebi, J. G. Yim, N. Birkbeck, B. Adsumilli, P. Milanfar, and F. Yang, Rich features for perceptual quality assessment of UGC videos, CVPR 2021.

[24] X. Luo , H. Talebi, F. Yang, M. Elad, and P. Milanfar, The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study, DCC 2021.

[23] Q. Wang, J. Ke, J. Greaves, G. Chu, G. Bender, L. Sbaiz, A. Go, A. Howard, M.-H. Yang, J. Gilbert, P. Milanfar and F. Yang, Multi-path Neural Networks for On-device Multi-domain Visual Classification, WACV 2021.

[22] Y. Wang, H. Talebi, F. Yang, J. G. Yim, N. Birkbeck, B. Adsumilli and P. Milanfar, Video transcoding optimization based on input perceptual quality, Proc. SPIE 11510, Applications of Digital Image Processing XLIII, 1151015, August 21, 2020.

[21] X. Zhu, H. Talebi, X. Shi, F. Yang, and P. Milanfar, Super-Resolving Commercial Satellite Imagery Using Realistic Training Data, ICIP 2020.

[20] I. Yoo, X. Luo, Y. Wang, F. Yang, and P. Milanfar, GIFnets: Differentiable GIF Encoding Framework, CVPR 2020.

[19] X. Luo , R. Zhan, H. Chang , F. Yang , and P. Milanfar, Distortion Agnostic Deep Watermarking, CVPR 2020.

[18] J. Zhang, F. Yang, T. Vogelsang, D. Stork and M. Vetterli. Multichannel sampling of low light scenes with unknown shifts , In Proc. of IEEE International Conference on Image Processing , Melbourne, Australia, Sep. 15-18, 2013.

[17] F. Yang, and M. Vetterli. Oversampled noisy binary image sensor. In Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, May 26-31, 2013. 

[16] Y. Wen, Z. Liu, W. Shi, Y. Jiang, A. Cheng, F. Yang and A. Kohar. Support for power efficient mobile video playback on simultaneous hybrid display. In Proc.  of the 10th IEEE Symposium on Embedded Systems for Real-time Multimedia, Tampere, Oct. 2012.

[15] Z. Chen, F. Yang, A. Lindner, G. Barrenetxea and M. Vetterli. How is the Weather: Automatic Inference from Images, In Proc. of IEEE International Conference on Image Processing, Orlando, USA, Sept. 30-Oct. 3, 2012.

[14] Y. Peng, F. Yang, Q. Dai, W. Xu and M. Vetterli. Super-resolution from unregistered aliased images with unknown scalings and shifts, In Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan, May 25-30, 2012.

[13] W. Shi, J. Yang, Y. Jiang, F. Yang and Y. Xiong. SenGuard: Passive User Identification on Smartphones Using Multiple Sensors, In Proc. of the 7th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, Shanghai, China, 2011.

[12] F. Yang, L. Sbaiz, E. Charbon, Y. Lu, S. Süsstrunk and M. Vetterli, The Gigavision Camera, Presented at: IEEE International Conference on Computational Photography, MIT, Boston, Massachusetts, USA, March 28-30, 2010. 

[11] F. Yang, Y.M. Lu, L. Sbaiz and M. Vetterli, An Optimal Algorithm for Reconstructing Images from Binary Measurements, In Proc. of IS&T/SPIE Electronic Imaging, Computational Imaging VIII, 2010. 

[10] F. Yang, L. Sbaiz, E. Charbon, S. Süsstrunk and M. Vetterli, On Pixel Detection Threshold in the Gigavision Camera, In Proc. of IS&T/SPIE Electronic Imaging, Digital Photography VI, Vol. 7537, 2010. 

[9] F. Yang, L. Sbaiz, E. Charbon, S. Süsstrunk and M. Vetterli, Image Reconstruction in the Gigavision Camera, IEEE 12th International Conference on Computer Vision, Ninth Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras, pp. 2212-2219, 2009. 

[8] L. Sbaiz, F. Yang, E. Charbon, S. Süsstrunk and M. Vetterli, The Gigavision Camera, In Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1093-1096, 2009. 

[7] G. Ding and F. Yang. A distributed video coding scheme based on denoising techniques. In Proc. of 13th Int. Multimedia Modeling Conference, LNCS 4351, pp.237-246, Singapore, Jan. 2007.

[6] C. Xue, L. Li, F. Yang, P. P. Wang, T. Wang, Y. Zhang, and Y. Sun. Automated home video editing: A multi-core solution. In Proc. of ACM 15th Int. Conference on Multimedia, pp.453-454, Augsburg, Sep. 2007.

[5] F. Yang, Q. Dai, and G. Ding. Multi-view images coding based on multiterminal source coding. In Proc. of IEEE Int. Conference on Acoustics, Speech and Signal Processing, pp.1037-1040, Honolulu, Apr. 2007.

[4] F. Yang, G. Ding, Q. Dai, and Y. Yin, Wavelet based scalable Wyner-Ziv video coding, In Proc. of Int. Picture Coding Symposium, Beijing, Apr. 2006.

[3] G. Ding, Q. Dai, Y. Yin, and F. Yang, Scalable video coding based on Wyner-Ziv framework, In Proc. of IEEE Visual Communications and Image Processing, Beijing, Jul. 2005.

[2] G. Ding, Q. Dai, F. Yang, and Y. Yin, A new region-of-interest image compression method based on Wyner-Ziv coding, In Proc. of IEEE Visual Communications and Image Processing, Beijing, Jul. 2005.

[1] F. Yang, G. Ding, Q. Dai and Y. Yin, Adaptive key frame selection Wyner-Ziv video coding, In Proc. of IEEE 7th Workshop on Multimedia Signal Processing, Shanghai, Oct. 2005.

[24] Xiyang Luo, Feng Yang, Elnaz Barshan Tashnizi, Dake He, Ryan Matthew Haggarty, Michael Gene Goebel, End-to-end watermarking system, US20230362399A1. 

[23] Innfarn Yoo, Xiyang Luo, Feng Yang, Encoders for improved image dithering, US11790564B2.

[22] Dake He, Tianhao Zhang, Elnaz Barshan Tashnizi, Xiyang Luo, Huiwen Chang, Feng Yang, Ryan Matthew Haggarty, Zoom agnostic watermark extraction, US20230325961A.

[21] Yilin Wang, Balineedu Adsumilli, Junjie Ke, Hossein Talebi, Joong Yim, Neil Birkbeck, Peyman Milanfar, Feng Yang, Methods, systems, and media for determining perceptual quality indicators of video content items, US20230319327A1.

[20] Qifei Wang, Junjie Ke, Grace Chu, Gabriel Mintzer Bender, Luciano Sbaiz, Feng Yang, Andrew Gerald Howard, Alec Michael Go, Jeffrey M Gilbert, Peyman Milanfar, Joshua William Charles Greaves, Systems and Methods for Generation of Machine-Learned Multitask Models, US20230267307A1. 

[19] Junjie Ke, Feng Yang, Qifei Wang, Yilin Wang, Peyman Milanfar, Multi-scale transformer for image analysis, US20230222623A1.

[18] Innfarn Yoo, Xiyang Luo, Feng Yang, Ondrej Stava, Systems and Methods for Message Embedding in Three-Dimensional Image Data, US20230214953A1. 

[17] Xiyang Luo, Feng Yang, Hossein Talebi, Generating quantization tables for image compression, US 2023/0130410 A1.

[16] Yilin Wang, Balineedu Adsumilli, Feng Yang, Debanding Using A Novel Banding Metric, US 2023/0131228 A1.

[15] Ruohan Zhan, Feng Yang, Xiyang Luo, Peyman Milanfar, Huiwen Chang, Ce Liu, Image watermarking, US 2023/0111326 A1.

[14] Qifei Wang, Alexander Kuznetsov, Alec Michael Go, Grace Chu, Eunyoung Kim, Feng Yang, Andrew Gerald Howard, Jeffrey M Gilbert, Systems and Methods for Improved Computer Vision in On-Device Applications, US 2023/0091374 A1.

[13] Xiyang Luo, Innfarn Yoo, Feng Yang, Deep palette prediction, US 2023/0053317 A1.

[12] Yilin Wang, Hossein Talebi, Peyman Milanfar, Feng Yang, Balineedu Adsumilli, Systems and Techniques for Retraining Models for Video Quality Assessment and for Transcoding Using the Retrained Models, US 2022/0415039 A1.

[11] Innfarn Yoo, Feng Yang, Xiyang Luo, Watermark-Based Image Reconstruction, US 2022/0335560 A1.

[10] Catherine Shyu, Xiyang Luo, Feng Yang, Junjie Ke, Yicong Tian, Chao-Hung Chen, Xia Li, Luying Li, Wenjing Kang, Shun-Chuan Chen, Evaluating visual quality of digital content, US 2022/0301141 A1.

[9] Innfarn Yoo, Xiyang Luo, Feng Yang, Encoders for Improved Image Dithering, US 2021/0304445 A1.

[8] P. Milanfar, F. Yang, S. Choi, Adaptive DCT Sharpener, US 2020/0186836 A1.

[7] F.  Yang, P. Milanfar, Y. Shen, J. Wang, Methods and apparatus to reduce compression artifacts in images, US 10,083,499 B1.

[6] F. Yang, Y. Lu, M. Vetterli, Method, apparatus and system for image acquisition and conversion, WO 2011089165, US 8,319,855 B2.

[5] F. Yang, Y. Lu, M. Vetterli, Image acquisition using oversampled one-bit poisson statistics, US 9,001,231 B2.

[4] W.D. Shi, J. Yang, F. Yang, Y.G. Xiong. Apparatus and methods of passive user identification using multiple sensing devices on a mobile computing system, US 20120167170 A1.

[3] Q. Dai, F. Yang, and G. Ding, A method for video compression supporting random access video playback, CN 101005622.

[2] Q. Dai, F. Yang, and G. Ding, A method for robust image compression based on distributed source coding, CN 1988670.

[1] G. Ding, Q. Dai, Z. Yu, and F. Yang, A method for robust video coding without prediction circle, CN 1889687.

[1] F. Yang, Y. Tian, X. Li, P. Milanfar, J. Wang, Adaptive Image Transcoding, 2020.

[1] F. Yang, Y.M. Lu, L. Sbaiz and M. Vetterli, Bits from Photons: Oversampled Image Acquisition Using Binary Poisson Statistics , Ecole Polytechnique Fédérale de Lausanne, Tech. Rep. 166345, Jun. 2011.

Hosted Interns

Teaching assistant

Project supervisor

Master thesis project

[1] Junjun Zhang, Multi-frame imaging system, fall~2012

Master semester project

[7] Céline Heldner, See through scattering, spring~2013

[6] Fréjaville Camille Chloé Emmeline, Visual tour: scene summarization for a city, fall~2012

[5] Sergiu Gaman, Video stabilization using Kinect camera, spring~2012

[4] Uday Takyar, Mobile phone as an image scanner, fall~2011

[3] Ljupce Nikolov, Video stabilization, co-advised with Yigang Peng from Tsinghua University, fall~2011

[2] Alexandre Chappuis, Tag your memory with colors: Semi-automatic recoloring on interested objects via hypergraph learning, co-advised with Li Pu from EPFL, fall~2011

[1] Jonathan Pittet, Mobile phone as an image scanner, co-advised with Kari Pulli from Nokia, spring~2011