Liu Ren, Ph.D.

Contact info: williamren at gmail dot com
Dr. Liu Ren is currently VP and Chief Scientist in Robert Bosch Research at Silicon Valley, CA. He is responsible for shaping strategic directions and developing cutting-edge technologies in the field of applied AI focusing on integrated Human-Machine Intelligence (HMI) for Robert Bosch Corporation, a multi-national corporation with over $70 Billion revenue and more than 400,000 employees worldwide.  


As the responsible global head, Liu oversees research activities conducted by several research departments and teams located in the Silicon Valley (U.S.), Pittsburgh (U.S.), and Renningen (Germany). Our applied AI research includes Big Data Visual AnalyticsExplainable AIConversational AI, Natural Language Processing (NLP), Computer PerceptionMixed Reality/ARAudio AnalyticsWearable Analytics, etc for IoT (Internet of Things) application areas such as autonomous driving, car infotainment and driver assistance systems (ADAS), Industry 4.0, smart home/building solutions, and robotics, etc. Many of his research results have led to good product impact (e.g., Bosch Intelligent Glove博世智能手套)  In particular, he led the R&D efforts for Robert Bosch's 3D artMap (Chinese: 三维艺术导航地图, the world's first stylized 3D navigation map powered by non-photorealistic (artistic) rendering technologies, which has been used in many products since 2010.). Since 2013, he has also led Bosch Research's R&D efforts to develop novel HMI/AI technologies in a high profile cross-unit project with Bosch Car Multimedia for Bosch's yearly CES (Consumer Electronics Show) demonstration. He has won the Bosch North America Inventor of the Year Award for 3D maps (2016),  Best Paper Award (2018), and Best Paper Honorable Mention Award (2016) for big data visual analytics in IEEE Visualization Conference (VAST).


Liu received his Ph.D. and M.Sc. degrees in Computer Science from Computer Science DepartmentCarnegie Mellon University, under the supervision of Prof.Jessica Hodgins. His Ph.D. work focused on data-driven character animation that spans the areas of machine learning, computer graphics and computer vision. He received B.Sc. and M.Sc. degrees on AI from Computer Science Department of Zhejiang University in China.

Selected Publications (Full list: Google Scholar)
Yao Ming, Panpan Xu, Furui Cheng, Huamin Qu, Liu Ren, "ProtoSteer: Steering Deep Sequence Model with Prototypes", video,  IEEE Transactions on Visualization and Computer Graphics 2020 (IEEE VAST 2019)

Summary: ProtoSteer enabling experts to inspect, critique, and revise explainable AI (XAI) models  (represented as a small set of prototypes) interactively with domain know-how for different AI applications (e.g., NLP,  predictive diagnostics).
 
 Yulin Yang, Benzun Pious Wisely Babu, Chuchu Chen, Guoquan Huang, Liu Ren, "Analytic Combined IMU Integration (ACI^2) For Visual Inertial Navigation", 2020 IEEE International Conference on Robotics and Automation (ICRA 2020)

Summary: Addressing key performance bottlenecks in visual-inertial sensor fusion: a modularized analytic combined IMU integrator (ACI^2) with elegant derivations for IMU integrations, bias Jabcobians and related covariances. 
 Yao Ming, Panpan Xu, Huamin Qu, Liu Ren, "Interpretable and Steerable Sequence Learning via Prototypes", video, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM KDD 2019), Research Track, Oral 

Summary: A novel interpretable and steerable deep sequence model (ProSeNet) for explainable AI with natural explanations derived from case-based reasoning. 
 Benzun Pious Wisely Babu, Zhixin Yan, Mao Ye, Liu Ren, "On Exploiting Per-Pixel Motion Conflicts to Extract Secondary Motions", video,IEEE International Symposium on Mixed and Augmented Reality 2017 (ISMAR 2018)

Summary: A novel approach addressing motion conclit problems in visual-inertial sensor fusion, enabling better augmentation of virtual content attached to secondary motions for Ubiquitous Augmented Reality (AR).
 

Dongyu Liu, Panpan Xu, Liu Ren, "TPFlow: Progressive Partition and Multidimensional Pattern Extraction for Large-Scale Spatio-Temporal Data Analysis", video,  IEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2018)Best Paper Award


Summary: A first visual analytics solution to handle multidimensional (>2D) spatial temporal data analysis for easy extraction and intuitive visualization of latent patterns based on a novel piecewise rank-one tensor decomposition algorithm.


 

Gromit Yeuk-Yin Chan, Panpan Xu, Zeng Dai, Liu Ren,
 "ViBR: Visualizing Bipartite Relations at Scale with the Minimum Description Length Principle", videoIEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2018)
 

Summary: A novel visual summarization technique for interactive analysis of large bipartite graphs based on the minimum description length (MDL) principle and locality sensitive hashing (LSH). 


 


 

Zhixin Yan, Mao Ye, and Liu Ren, "Dense Visual SLAM with Probabilistic Surfel Map", videoIEEE International Symposium on Mixed and Augmented Reality 2017 (ISMAR 2017), and selected for TVCG publication (IEEE Transactions on Visualization and Computer Graphics).

Summary: A novel map representation called Probabilistic Surfel Map (PSM) that provides globally consistent map of the environment for dense visual SLAM, leading to a drastic performance improvement (e.g, tracking errors) compared to the state of the art approach (e.g, σ-DVO) 

 

 
Alsallakh Bilal, Amin Jourabloo, Mao Ye, Xiaoming Liu, and Liu Ren, "
Do Convolutional Neural Networks Learn Class Hierarchy?"
, video, IEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2017)

Summary: A novel explainable AI approach that can help to improve the performance of general CNN-based classifiers with ease by leveraging visual analytics to improve CNN model structure and identify issues in the training data 


 



 
Yuanzhe Chen, Panpan Xu, and Liu Ren, "Sequence Synopsis: Optimize Visual Summary of Temporal Event Data", video, supplementary material,  IEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2017).

Summary:
A novel event sequence summarization and visualization approach based on the minimum description length (MDL) principle addressing several key AI application areas (e.g., predictive diagnostics for connected vehicles)

 
 
Amin Jourabloo,  Xiaoming Liu,  Mao Ye, and  Liu Ren
, "Pose-Invariant Face Alignment with a Single CNN"video International Conference on Computer Vision (ICCV 2017).

Summary: 
A novel large-pose face alignment method with fast end-to-end training in a single CNN
 


Panpan Xu, Honghui Mei, Liu Ren,
  and Wei Chen, 
ViDX: Visual Diagnostics of Assembly Line Performance in Smart Factories”,   videoIEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2016),  Best Paper Honorable Mention Award.

Summary: A first visual analytics approach to addressing the needs (e.g., easy process optimization and intuitive troubleshooting for manufacturing)  of a new application domain-Industry 4.0 or Connected Industry 


 



B
ilal Alsallakh and Liu Ren
PowerSet: A Comprehensive Visualization of Set Intersections”, videoIEEE Transactions on Visualization and Computer Graphics (IEEE Info VIS 2016).


Summary: A simple and novel set visualization approach for various kinds of big data analytics applications (e.g., predictive analytics) 


 


 
Chao Du, Yen-Lin Chen, Mao Ye, and Liu Ren
Edge Snapping-Based Depth Enhancement for Dynamic Occlusion Handling in Augmented Reality”,  videoIEEE International Symposium on Mixed and Augmented Reality 2016,  (full paper for ISMAR 2016).

Summary: A near real-time approach to dealing with dynamic occlusion handling challenges with high quality visual presentations for both video see-through and optics see-through AR applications  


 

 
Benzun Wisely Babu, Soohwan Kim, Zhixin Yan, and Liu Ren
σ-DVO: Sensor Noise Model Meets Dense Visual Odometry”, videoIEEE International Symposium on Mixed and Augmented Reality 2016,  (full paper for ISMAR 2016).


Summary: A novel dense tracking approach by incorporating uncertainty modeling of depth measurements in the optimization framework of RGBD sensing for AR,  leading to a drastic 25% error reduction compared to the state-of-the art solution 


 


 

Jennifer Chandler, Lei Yang and Liu Ren"Procedural Window Lighting Effects for Real-Time City Rendering", videoACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D) 2015.


Summary: A fast and scalable approach to addressing challenges in large scale  night view rendering for big cities with applications in computer graphics and real-time geo-visualization for future infotainment systems

mocapICCV2011

Mao Ye, Xianwang Wang, Ruigang Yang, Liu Ren, and Marc Pollefeys, "Accurate 3D Body Pose Estimation From a Single Depth Image", Proceedings of International Conference on Computer Vision (ICCV 2011), November, 2011 

Summary: A high accurate human pose estimation algorithm for entertainment applications that employ a depth sensor as input

iriscaptureCVPR2009
 
Xinyu Huang, Liu Ren, and Ruigang Yang, "Image Deblurring for Less Intrusive Iris Capture",  IEEE Computer Society Coference on Computer Vision and Pattern Recognition (CVPR 2009), June, 2009

Summary: A long range and non-intrusive iris capture and recognition system featuring a novel image deblurring algorithm to handle the limitation of low cost hardware (patent granted)
naturalmotionSIG05

 

Liu Ren, Alton Patrick, Alexei Efros, Jessica Hodgins, and James Rehg, "A Data-Driven Approach to Quantifying Natural Human Motion", ACM Transactions on Graphics (SIGGRAPH 2005),  August, 2005.

Summary: The first approach to automatic human animation quality evaluation

SwingTog05
 
 

Liu Ren, Gregory Sharknarovich, Jessica Hodgins, Hanspeter Pfister and Paul Viola, "Learning Silhouette Features for Control of Human Motion", ACM Transactions on Graphics (SIGGRAPH 2004),  October, 2005.

Summary: A novel and low cost vision-based interface for "do-as-I-do" applications in entertainment industry

engineIEEEVIS04

 


Wei Chen, Liu Ren, Matthias Zwicker and Hanspeter Pfister, "Hardware-Accelerated Adpative EWA Volume Splatting", IEEE Visualization 2004, October, 2004.

Summary: The first GPU-based approach to high quality volume splatting with EWA filtering (patent granted)

waspEG02

 

Liu Ren, Hanspeter Pfister and Matthias Zwicker, "Object Space EWA Surface Splatting: A Hardware Accelerated Approach to High Quality Point Rendering",  Computer Graphics Forum 21(3)( EUROGRAPHICS 2002, Best Paper Nominee), September, 2002.

Summary: The first GPU-based approach to high quality point-based rendering with EWA filtering (patent granted)

Selected Products 
3D artMap (Berlin, watercolor, day mode)







3D artMap (watercolor & pencil hatching style, Berlin and Stuttgart)

3D artMap is
the world's first stylized 3D navigation map powered by non-photorealistic (artistic ) rendering technologies.  3D artMap is the key feature
in Robert Bosch's first iPhone app product (successfully launched in 2010.12 for 19 european countries) and several in-car navigation products. 


SelectionFile type iconFile nameDescriptionSizeRevisionTimeUser
Comments