Yasutaka Furukawa's Homepage

Yasutaka Furukawa

Principal Scientist
Wayve
Associate Professor
GrUVi Lab, SFU

Email: furukawa (at) sfu.ca
Office: TASC I 8023
Mail address: click here

Bio (CV, Google scholar)
I am a principal scientist at Wayve and an associate professor of Computing Science at Simon Fraser University. Prior to SFU, I was an assistant professor at Washington University in St. Louis. Before WUSTL, I was a software engineer at Google. Before Google, I was a post-doctoral research associate at University of Washington. I worked with Prof. Seitz and Prof. Curless at University of Washington, and Rick Szeliski at Facebook (was at Microsoft Research). I completed my Ph.D. under the supervision of Prof. Ponce at Computer Science Department of University of Illinois at Urbana-Champaign in May 2008. I received PAMI Longuet-Higgins prize (2020), CS-CAN: Outstanding Young CS Researcher Award (2018), NSF CAREER Award (2015), Best Student Paper Award at ECCV 2012, and Google Faculty Research Awards (2018, 2017, 2016).

SFU Visual Computing Groups

(Ranked 12th in the world in Computer Vision and Graphics as of 2022.01)

Group photographs

At CVPR 2024, Seattle.
At CVPR 2023, Vancouver.
At SFU 2022, Vancouver.
At ICCV 2019, Seoul.

How to join my group?

I am recruiting graduate students. Please drop me an email with your resume/CV. However, I am likely unable to reply to individual inquiries due to the volume.

Financial supporters

Recent Projects

News

Taks at KCCV, Kyoto-U, and Tokyo-U, August 2023
Talk at CVPR workshop June 2023
Talks at U-Tokyo, Tokyo-Institute-Tech, and Korea AI Summit, December 2022
Keynote at 3DV, September 2022
Talk at Amazon Computer Vision Conference, August 2022.
Talk at SFU AI4ALL event, July 2022.
Talk at 3rd OmniCV workshop, June CVPR2022.
Talk at TU Delft seminar, April 2022.
Talk at UCSD Pixel Cafe seminar, March 2022.

PAMI Longuet-Higgins prize at CVPR2020.
Program Chair for ICCV 2023.
Congrats Nelson for winning Borealias AI Fellowship.
Congrats Sachini and Jiacheng for winning Graduate Dean Entrance Scholorship.
News about the team here, here, and there.
DND/NSERC Supplement Grants (2018.8 - 2021.7)
NSERC DAS Grants (2018.4 - 2021.3)
CS-CAN, Outstanding Young CS Researcher Award (2018)
Google Research Awards (2018, 2017, and 2016)
PMVS for 2000-year-old skull or saving wild animals.
Received NSF CAREER Award (starting Feb 2015).

Projects

	BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry Xiang Xu, Joseph G. Lambourne, Pradeep Kumar Jayaraman, Zhengqing Wang, Karl D.D. Willis, Yasutaka Furukawa SIGGRAPH 2024. Project website		MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping Jiacheng Chen, Yuefan Wu, Jiaqi Tan*, Hang Ma, Yasutaka Furukawa ECCV 2024 (oral). Project website
	MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single to Sparse-view 3D Object Reconstruction Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan ECCV 2024. Project website		Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation Mohammad Amin Shabani, Zhaowen Wang, Difan Liu, Nonxuan Zhao, Jimei Yang, and Yasutaka Furukawa CVPR 2024.
	A-Scan2BIM: Assistive Scan to Building Information Modeling Weilian Song, Jieliang Luo, Dale Zhao, Yan Fu, Chin-Yi Cheng, and Yasutaka Furukawa BMVC 2023 (oral).		Floorplan Restoration by Structure Hallucinating Transformer Cascades Sepidehsadat Hosseini and Yasutaka Furukawa BMVC 2023.
	MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion Shitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang, and Yasutaka Furukawa NeurIPS 2023 (spotlight). Project website. Hugging Face Demo.		PuzzleFusion: Unleasing the Power of Diffusion Models for Spatial Puzzle Solving Sepidehsadat Hosseini, Mohammad Amin Shabani, Saghar Irandoust, and Yasutaka Furukawa NeurIPS 2023 (spotlight). Project website.
	PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models Jiacheng Chen, Ruizhi Denge, and Yasutaka Furukawa NeurIPS 2023. Project website.		Hierarchical Neural Coding for Controllable CAD Model Generation Xiang Xu, Pradeep Kumar Jayaraman, Joseph George Lambourne, Karl D.D. Willis, and Yasutaka Furukawa ICML 2023. Project website.
	NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization Shitao Tang, Sicong Tang, Andrea Tagliasacchi, Ping Tan, and Yasutaka Furukawa CVPR 2023. Project website.		HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising Amin Shabani, Sepidehsadat Hosseini, and Yasutaka Furukawa CVPR 2023. Project website.
	Hierarchical Neural Memory Network for Low Latency Event Processing Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, and Ken Sakurada CVPR 2023. Project website.		Vectorizing Building Blueprints Weilian Song, Mahsa Maleki Abyaneh, Mohammad Amin Shabani, and Yasutaka Furukawa ACCV 2022.
	SkexGen: Generating CAD Construction Sequences by Autoregressive VAE with Disentangled Codebooks Xiang Xu, Karl Willis, Joseph Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa ICML 2022. Project website.		Neural Inertial Localization Sachini Herath, David Caruso, Chen Liu, Yufan Chen, and Yasutaka Furukawa CVPR 2022. Project website.
	HEAT: Holistic Edge Attention Transformer for Structured Reconstruction Jiacheng Chen, Yiming Qian, and Yasutaka Furukawa CVPR 2022. Project website.		Single User WiFi Structure from Motion in the Wild Yiming Qian, Hang Yan, Sachini Herath, Pyojin Kim, and Yasutaka Furukawa ICRA 2022.
	Extreme Structure from Motion for Indoor Panoramas without Visual Overlaps Amin Shabani, Weilian Song, Hirochika Fujiki, Makoto Odamaki, and Yasutaka Furukawa ICCV 2021. Supplementary document.		Structured Outdoor Architecture Reconsruction by Exploration and Classification Fuyang Zhang, Sam Xu, Nelson Nauata, and Yasutaka Furukawa ICCV 2021. Project website. Supplementary document.
	Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses Yiming Qian, Hao Zhang, and Yasutaka Furukawa CVPR 2021. Project website. Supplementary document.		House-GAN++: Generative Adversarial Layout Refinement Networks Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu, Chin-Yi Cheng, and Yasutaka Furukawa CVPR 2021. Project website. Online interactive browser demo! Supplementary document.
	Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, and Ken Sakurada. CVPR 2021.		Plan2Scene: Converting Floorplans to 3D Scenes Madhawa Vidanapathirana, Qirui Wu, Yasutaka Furukawa, Angel Chang, and Manolis Savva CVPR 2021. Project website.
	Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments Sachini Herath, Saghar Irandoust, Bowen Chen, Yiming Qian, Pyojin Kim, and Yasutaka Furukawa ICRA 2021. Project website.		House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, and Yasutaka Furukawa ECCV 2020 (oral). Project website. Interactive demo video.
	Vectorizing world buildings: Planar graph reconstruction by primitive detection and relationship inference Nelson Nauata and Yasutaka Furukawa ECCV 2020. Project website.		Learning Inter-Plane Relations for Piecewise Planar Reconstruction Yiming Qian and Yasutaka Furukawa ECCV 2020. Project website.
	Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction Fuyang Zhang, Nelson Nauata, and Yasutaka Furukawa (* indicates equal contribution) CVPR 2020. Project website. Supplementary document.		Bundle Pooling for Polygonal Architecture Segmentation Problem Huayi Zeng, Kevin Joseph, Adam Vest, and Yasutaka Furukawa CVPR 2020.
	Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path Jiacheng Chen, Chen Liu, Jiaye Wu, and Yasutaka Furukawa ICCV 2019. Video. Project website. Supplementary document.		SANet: Scene Agnostic Network for Camera Localization Luwei Yang, Ziqian Bai, Chengzhou Tang, Honghua Li, Yasutaka Furukawa, and Ping Tan ICCV 2019. Supplementary document.
	RoNIN: Robust Neural Inertial Navigation in the Wild Hang Yan, Sachini Herath, and Yasutaka Furukawa (* indicates equal contribution) ICRA 2020 arXiv:1905.12853 Video. Project website.		PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image Chen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, Jan Kautz CVPR 2019 (oral). arXiv:1812.04072 Project website.
	Neural Procedural Reconstruction for Residential Buildings Huayi Zeng, Jiaye Wu, and Yasutaka Furukawa ECCV 2018. Video.		FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans Chen Liu, Jiaye Yu, and Yasutaka Furukawa (* indicates equal contribution) ECCV 2018. Video. Project website
	RIDI: Robust IMU Double Integration Hang Yan, Qi Shan, and Yasutaka Furukawa ECCV 2018. Video. Project website.		Polarimetric Dense Monocular SLAM Luwei Yang, Feiton Tan, Ao Li, Zhaopeng Cui, Yasutaka Furukawa, and Ping Tan. CVPR 2018 (oral). Supplementary material.
	PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image Chen Liu, Jimei Yang, Duygu Ceylan, Ersin Yumer, and Yasutaka Furukawa CVPR 2018 (spotlight). Project website Supplementary material.		Raster-to-Vector: Revisiting Floorplan Transformation Chen Liu, Jiajun Wu, Pushmeet Kohli, and Yasutaka Furukawa ICCV 2017. Video. Supplementary material. A project website. Code and data.
	Exploiting 2D Floorplan for Building-scale Panorama RGBD Alignment Erik Wijmans and Yasutaka Furukawa CVPR 2017 Arxiv:1612.02859. Project page. Video. Video highlight.		Deep Multi-Modal Image Correspondence Learning Chen Liu, Jiajun Wu, Pushmeet Kohli, and Yasutaka Furukawa arXiv:1612.01225. Video.
	Turning an Urban Scene Video into a Cinemagraph Hang Yan, Yebin Liu, and Yasutaka Furukawa CVPR 2017 arXiv:1612.01235. Video.		Panoramic Structure from Motion via Geometric Relationship Detection Satoshi Ikehata, Ivaylo Boyadzhiev, Qi Shan, and Yasutaka Furukawa arXiv:1612.01256. Video.
	Multi-way Particle Swarm Fusion Chen Liu, Hang Yan, Pushmeet Kohli, and Yasutaka Furukawa arXiv:1612.01234.		Layered Scene Decomposition via the Occlusion-CRF Chen Liu, Pushmeet Kohli, and Yasutaka Furukawa CVPR 2016 (spotlight). Video. Code. Supplementary material.
	Structured Indoor Modeling Satoshi Ikehata, Hang Yan, and Yasutaka Furukawa ICCV 2015 (oral). Project website.		Multi-View Stereo: A Tutorial Yasutaka Furukawa and Carlos Hernandez Foundations and Trends in Computer Graphics and Vision, 2015.
	Accurate Geo-registration by Ground-to-Aerial Image Matching Qi Shan, Changchang Wu, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz 3DV 2014 (oral). Project website.		Photo Uncrop Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz ECCV 2014. Project website.
	Piecewise Planar and Compact Floorplan Reconstruction from Images Ricardo Cabral and Yasutaka Furukawa CVPR 2014. Video. Supplementary material.		Occluding Contours for Multi-View Stereo Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, and Steven M. Seitz CVPR 2014. A project website with more contents.
	The Visual Turing Test for Scene Reconstruction - (supplementary document.) Qi Shan, Riley Adams, Brian Curless, Yasutaka Furukawa, and Steven M. Seitz 3DV 2013 (oral). Best Paper Award. A project website with more contents.		Reconstructing the World's Museums Jianxiong Xiao and Yasutaka Furukawa IJCV 2014. Reconstructing the World's Museums - (supplementary document) Jianxiong Xiao and Yasutaka Furukawa ECCV 2012 (oral). Best Student Paper Award. Selected as a 2012 excellent paper by Google Research.
	Google Maps - Photo Tours, April, 2012 Designed and implemented a pipeline to compute scene geometries for rendering and "3D Ken Burns" motions. Examples (a few clicks away). Photo Tours Avanish Kushal, Ben Self, Yasutaka Furukawa, David Gallup, Carlos Hernandez, Brian Curless, and Steve Seitz 3DimPVT 2012 (oral).		MapsGL (Next generation Google Map), October, 2011 Designed and implemented a city-scale dense 3D reconstruction pipeline from aerial images, running in an unprecedented scale for hundreds of cities all over the world.
	Building Rome in a Day Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Brian Curless, Steven M. Seitz and Richard Szeliski Communications of the ACM, Vol. 54, No. 14, Pages 105-112, October 2011. Building Rome Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Brian Curless, Steven M. Seitz and Richard Szeliski IEEE Computer Society, June 2010.		Towards Internet-scale Multi-view Stereo (supplementary material) Yasutaka Furukawa, Brian Curless, Steven M. Seitz and Richard Szeliski CVPR 2010. CMVS software available! Project website coming soon.
	Reconstructing Building Interiors from Images Yasutaka Furukawa, Brian Curless, Steven M. Seitz and Richard Szeliski ICCV 2009 (oral). Project website.		Dense 3D Motion Capture for Human Faces Yasutaka Furukawa and Jean Ponce CVPR 2009.
	Manhattan-world Stereo Yasutaka Furukawa, Brian Curless, Steven M. Seitz and Richard Szeliski CVPR 2009. Movie		Dense 3D Motion Capture from Synchronized Video Streams Yasutaka Furukawa and Jean Ponce CVPR 2008. (oral) Dense Patch Models for Motion Capture from Synchronized Video Streams Yasutaka Furukawa and Jean Ponce -- Willow Tech. Report 02-07
	Accurate Camera Calibration from Multi-View Stereo and Bundle Adjustment Yasutaka Furukawa and Jean Ponce IJCV, 2009. Accurate Camera Calibration from Multi-View Stereo and Bundle Adjustment Yasutaka Furukawa and Jean Ponce CVPR 2008.		Accurate, Dense, and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce PAMI, August 2010. Accurate, Dense, and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce CVPR 2007.
	Carved Visual Hulls for Image-Based Modeling Yasutaka Furukawa and Jean Ponce IJCV, March 2008 Special Issue: Best of the European Conference on Computer Vision 2006 Carved Visual Hulls for Image-Based Modeling Yasutaka Furukawa and Jean Ponce ECCV 2006. (oral)		Projective Visual Hulls IJCV, August 2007 Svetlana Lazebnik, Yasutaka Furukawa and Jean Ponce
	Robust Structure and Motion from Outlines of Smooth Curved Surfaces Yasutaka Furukawa, Amit Sethi, Jean Ponce, and David Kriegman. PAMI, February 2006 (Vol. 28, No. 2) pp.302-315 Structure and Motion from Images of Smooth Textureless Objects Yasutaka Furukawa, Amit Sethi, Jean Ponce, and David Kriegman. ECCV 2004.		Accurate and Robust Line Segment Extraction by Analyzing Distribution around Peaks in Hough Space Yasutaka Furukawa and Yoshihisa Shinagawa Computer Vision and Image Understanding Volume 92, Issue 1, Pages 1-25 (October 2003)

Members

Past members

Nelson Nauata. Apple (SFU Ph.D., 2022)
Saghar Irandoust. Borealis AI (SFU M.Sc., 2022)
Yiming Qian. Assistant Professor at University of Manitoba (Postdoc, 2022)
Mahsa Abyaneh. LivingCities (SFU M.Sc., 2021)
Huayi Zeng. Waymo (WUSTL Ph.D., 2021)

Kevin Joseph. Software engineer at Motion Metrics (SFU M.Sc., 2021)

Pyojin Kim. Assistant Professor at Sookmyung Women's University (SFU postdoc, 2020)
Bowen Chen. (SFU undergraduate, 2020)
Chen Liu. Facebook Reality Lab (WUSTL Ph.D., 2019)
Hang Yan. Waymo (WUSTL Ph.D., 2019)
Jiacheng Chen. USC graduate student (SFU undergraduate, 2019)
Jun XU. Assistant Professor at Nankai University (SFU postdoc, 2019)
Charlie Wu. UMD graduate student (WUSTL undergraduate, 2019)
Adam Patrick. NIKE (Fulbright scholar at SFU, 2019)
Leo Li. University of Toronto graduate student (SFU undergraduate, 2018)
Erik Wijmans. Georgia Tech graduate student (WUSTL undergraduate, 2017)
Patrick Sullivan. Boeing (WUSTL Master, 2017)
Jeanine Burke. Microsoft software developper (WUSTL undergraduate, 2016)
Xinyi Gong. Amazon software engineer (WUSTL undergraduate, 2016)
Satoshi Ikehata. Assistant Professor at National Institute of Informatics (WUSTL postdoc, 2016)
Moniqua Guo. Google (WUSTL undergraduate, 2015)
Brian Choi. Google (WUSTL master, 2014)

Teaching

CMPT412 Computer Vision: Fall 2023, Spring 2023, Fall 2021, Fall 2020, Fall 2019
CMPT762 Computer Vision: Fall 2023, Fall 2022, Spring 2022, Spring 2021, Spring 2020
Visual Computing Seminar: Fall 2018
CMPT822(7XX) Computer Vision: Fall 2018
CMPT469-888 Computational Photography: Winter 2018
Graphics and Vision seminar, Spring 2017
CSE559 Computer Vision: Fall 2016, Spring 2015, Fall 2013
ARCH529 New Vision: Designing for New Tools: Spring 2016, Spring 2015
CSE452 Computer Graphics: Spring 2016, Spring 2014

Resources

PMVS & CMVS