Angjoo Kanazawa

Angjoo Kanazawa 

I am an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. I lead the Kanazawa AI Research (KAIR) lab under BAIR. I serve on the advisory board of Wonder Dynamics.

Previously, I was a Research Scientist at Google Research, and BAIR postdoc at UC Berkeley advised by Jitendra Malik, Alexei A. Efros and Trevor Darrell. I completed my PhD in Computer Science at the University of Maryland, College Park with my advisor David Jacobs. During my PhD, I had the pleasure to visit the Max Planck Institute in Tübingen, Germany under the guidance of Michael Black.

CV | Google Scholar | twitter

Email: kanazawa (at) eecs.berkeley.edu


Dear prospective students: Click here for information.

News

Research

My research lies at the intersection of computer vision, computer graphics, and machine learning. We live in a 3D world that is dynamic, full of life with people and animals interacting with the environment. How can we build a system that can capture, perceive, and understand this 4D world from everyday photograph and video? How can we learn priors on the 4D world from image and video observations? The goal of my lab is to answer this question.

Kanazawa AI Research (KAIR) members

Postdoc

Graduate Students

5th year MS students

Alumni

Former PhD Students Former Postdocs Former MS/BS Students and Visitors

Libraries

viser gsplat

Preprints

Generative Proxemics: A Prior for 3D Social Interaction from Images
Lea Müller, Vickie Ye, Georgios Pavlakos, Michael Black, Angjoo Kanazawa
arXiv 2023
[project page] [arXiv preprint] [code] [bibtex]

Papers

LERF-TOGO: Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping
Adam Rashid*, Satvik Sharma*, Chung Min Kim, Justin Kerr, Lawrence Chen, Angjoo Kanazawa, Ken Goldberg
CORL 2023 Best Paper Finalist
[Project Page] [Code] [Paper] [bibtex]

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives
Tom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A. Efros, Mathieu Aubry
NeurIPS 2023
[Project Page] [Code] [Paper] [bibtex]

Humans in 4D: Reconstructing and Tracking Humans with Transformers
Shubham Goel, Georgios Pavlakos, Jathushan Rajasegaran, Angjoo Kanazawa*, Jitendra Malik*
ICCV 2023
[Project Page] [Code] [🤗Demo] [Paper] [bibtex]

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions
Ayaan Haque, Matthew Tancik, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa
ICCV 2023
[Project Page] [Code] [Paper] [bibtex]

LERF: Language Embedded Radiance Fields
Justin Kerr*, Chung Min Kim*, Ken Goldberg, Angjoo Kanazawa, Matthew Tancik
ICCV 2023
[Project Page] [Code] [Paper] [bibtex]

👻Nerfbusters🧹: Removing Ghostly Artifacts from Casually Captured NeRFs
Frederik Warburg*, Ethan Weber*, Matt Tancik, Aleksander Holynski, Angjoo Kanazawa
ICCV 2023
[Project Page] [Code] [Paper] [bibtex]

NerfAcc: Efficient Sampling Accelerates NeRFs
Ruilong Li, Hang Gao, Matthew Tancik, Angjoo Kanazawa
ICCV 2023
[Documentation] [Github] [Paper] [bibtex]

Nerfstudio: A Modular Framework for Neural Radiance Field Development
Matthew Tancik*, Ethan Weber*, Evonne Ng*, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, Angjoo Kanazawa
SIGGRAPH 2023 conference track
[Documentation] [Code] [Paper] [bibtex]

Decoupling Human and Camera Motion from Videos in the Wild
Vickie Ye, Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa
CVPR 2023
[Project Page] [Code] [Paper] [bibtex]

K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
Sara Fridovich-Keil*, Giacomo Meanti*, Frederik Rahbæk Warburg, Benjamin Recht, Angjoo Kanazawa
CVPR 2023
[Project Page] [Code] [Paper] [bibtex]

On the Benefits of 3D Pose and Tracking for Human Action Recognition
Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Christoph Feichtenhofer, Jitendra Malik
CVPR 2023
[Project Page]

Monocular Dynamic View Synthesis: A Reality Check
Hang Gao, Ruilong Li, Shubham Tulsiani, Bryan Russell, Angjoo Kanazawa
NeurIPS 2022
[Project Page] [Code] [Paper] [bibtex]

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
Zhengqi Li, Qianqian Wang, Noah Snavely, Angjoo Kanazawa
ECCV 2022 (Oral)
[Project Page] [Paper] [bibtex]

The One Where They Reconstructed 3D Humans and Environments in TV Shows
Georgios Pavlakos*, Ethan Weber*, Matthew Tancik, Angjoo Kanazawa
ECCV 2022
[Project Page] [Code and Data] [Paper] [bibtex]

TAVA: Template-free Animatable Volumetric Actors
Ruilong Li, Julian Tanke, Minh Vo, Michael Zollhoefer, Jurgen Gall, Angjoo Kanazawa, Christoph Lassner
ECCV 2022
[Project Page] [Code] [Paper] [bibtex]

Studying Bias in GANs through the Lens of Race
Vongani H. Maluleke*, Neerja Thakkar*, Tim Brooks, Ethan Weber, Trevor Darrell, Alexei A. Efros, Angjoo Kanazawa, Devin Guillory
ECCV 2022
[Project Page] [Code] [Paper] [bibtex]

Plenoxels: Radiance Fields without Neural Networks
Alex Yu*, Sara Fridovich-Keil*, Matthew Tancik, Qinhong Chen, Ben Recht, Angjoo Kanazawa
CVPR 2022 (Oral)
[Project Page] [Paper] [Code] [bibtex]

Deformable Sprites for Unsupervised Video Decomposition
Vickie Ye, Zhengqi Li, Richard Tucker, Angjoo Kanazawa, Noah Snavely
CVPR 2022 (Oral)
[Project Page] [Paper] [Code] [bibtex]

Tracking People by Predicting 3D Appearance, Location & Pose
Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik
CVPR 2022 (Oral)
[Project Page] [Paper] [Code] [bibtex]

Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion
Evonne Ng, Hanbyu Joo, Liwen Hu, Hao Li, Trevor Darrell, Angjoo Kanazawa, Shiry Ginosar
CVPR 2022
[Project Page] [Paper] [Code] [bibtex]

Human Mesh Recovery from Multiple Shots
Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa
CVPR 2022
[Project Page] [Paper] [bibtex]

Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image
Shizhan Zhu, Sayna Ebrahimi, Angjoo Kanazawa, Trevor Darrell
ICLR 2022
[Project Page] [Paper] [Code] [bibtex]

Tracking People with 3D Representations
Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik
NeurIPS 2021
[Project Page] [Paper] [Code] [bibtex]

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
Andrew Liu*, Richard Tucker*, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa
ICCV 2021 (Oral)
[Project Page with Demo] [Paper] [Code] [bibtex]

PlenOctrees for Real-time Rendering of Neural Radiance Fields
Alex Yu, Ruilong Li, Matthew Tancik, Hao Li, Ren Ng, Angjoo Kanazawa
ICCV 2021 (Oral)
[Project Page with Demo] [Paper] [Code] [bibtex]

Reconstructing Hand-Object Interactions in the Wild
Zhe Cao*, Ilija Radosavovic*, Angjoo Kanazawa, Jitendra Malik
ICCV 2021
[Project Page] [Paper] [MOW Dataset] [bibtex]

AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
Ruilong Li*, Shan Yang*, David A. Ross, Angjoo Kanazawa
ICCV 2021
[Project Page] [Paper] [Dataset] [Code] [bibtex]

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
Xue Bin Peng*, Ze Ma*, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa
SIGGRAPH 2021
[Project Page] [Paper] [Code] [bibtex]

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control
Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa
CVPR 2021 (Oral)
[Project website][Paper] [Code] [bibtex]

pixelNeRF: Neural Radiance Fields from One or Few Images
Alex Yu, Vickie Ye, Matthew Tancik, Angjoo Kanazawa
CVPR 2021
[Project Page/Code] [paper] [bibtex]

De-rendering the World's Revolutionary Artefacts
Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa
CVPR 2021
[Project website] [Paper] [bibtex]

An Analysis of SVD for Deep Rotation Estimation
Jake Levinson, Carlos Esteves, Kefan Chen, Noah Snavely, Angjoo Kanazawa, Afshin Rostamizadeh, Ameesh Makadia
NeurIPS 2020
[Github] [paper] [bibtex]

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild
Jason Y. Zhang*, Sam Pepose*, Hanbyul Joo, Deva Ramanan, Jitendra Malik, Angjoo Kanazawa
ECCV 2020
[project page] [Github] [arXiv preprint] [bibtex]

Shape and Viewpoint without Keypoints
Shubham Goel, Angjoo Kanazawa, Jitendra Malik
ECCV 2020
[project page] [Github] [arXiv preprint] [bibtex]

Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"
Silvia Zuffi, Angjoo Kanazawa, Tanya Berger-Wolf, Michael J. Black
ICCV 2019
[Github] [arXiv preprint] [bibtex]

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
Shunsuke Saito*, Zeng Huang*, Ryota Natsume*, Shigeo Morishima, Angjoo Kanazawa, Hao Li
(* equal contribution)
ICCV 2019
[project page] [arXiv preprint] [video] [bibtex]

Predicting 3D Human Dynamics from Video
Jason Y. Zhang, Panna Felsen, Angjoo Kanazawa, Jitendra Malik
ICCV 2019
[project page] [arXiv preprint] [video] [bibtex]

Learning 3D Human Dynamics from Video
Angjoo Kanazawa*, Jason Y. Zhang*, Panna Felsen*, Jitendra Malik
CVPR 2019
[project page] [arXiv preprint] [video] [bibtex]

Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine
ICLR 2019
[project page] [code] [arXiv preprint] [video] [bibtex]

SFV: Reinforcement Learning of Physical Skills from Videos
Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, Sergey Levine
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2018)
[project page] [pdf] [BAIR Blog] [arXiv preprint] [video] [bibtex]

  • Featured in two minute papers
  • Learning Category-Specific Mesh Reconstruction from Image Collections
    Angjoo Kanazawa*, Shubham Tulsiani*, Alexei A. Efros, Jitendra Malik
    (* equal contribution)
    ECCV 2018
    [project page] [pdf] [arXiv preprint] [video] [bibtex]

    End-to-end Recovery of Human Shape and Pose
    Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik
    CVPR 2018
    [project page with code] [pdf] [arXiv preprint] [bibtex]

    SfSNet : Learning Shape, Reflectance and Illuminance of Faces ‘in the wild’
    Soumyadip Sengupta, Angjoo Kanazawa, Carlos D. Castillo, David W. Jacobs
    CVPR 2018 (Spotlight)
    [project page with code] [pdf] [arXiv preprint] [bibtex]

    Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape from Images
    Silvia Zuffi, Angjoo Kanazawa, Michael J. Black
    CVPR 2018 (Spotlight)
    [project page with 3D models] [pdf] [bibtex]

    Towards Accurate Marker-less Human Shape and Pose Estimation over Time
    Yinghao Huang, Federica Bogo, Christoph Lassner, Angjoo Kanazawa, Peter V. Gehler, Javier Romero, Ijaz Akhter, Michael J. Black
    International Conference on 3D Vision (3DV), 2017.
    [pdf] [bibtex]

    3D Menagerie: Modeling the 3D shape and pose of animals
    Silvia Zuffi, Angjoo Kanazawa, David W. Jacobs, Michael J. Black
    Computer Vision and Pattern Recognition (CVPR) 2017. (Spotlight)
    [project page with model and demo] [pdf] [arXiv] [bibtex]

    Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
    Federica Bogo*, Angjoo Kanazawa*, Christoph Lassner, Peter Gehler, Javier Romero and Michael J. Black
    (* equal contribution)
    European Conference on Computer Vision (ECCV) 2016. (Spotlight)
    [pdf] [project page with code] [Spotlight video] [bibtex]

    WarpNet: Weakly Supervised Matching for Single-View Reconstruction
    Angjoo Kanazawa, David W. Jacobs, Manmohan Chandraker
    Computer Vision and Pattern Recognition (CVPR) 2016.
    [pdf] [supp] [test set ids & our curves] [bibtex]

    Learning 3D Deformation of Animals from 2D Images
    Angjoo Kanazawa, Shahar Kovalsky, Ronen Basri, David W. Jacobs
    Eurographics 2016. Best Paper Award
    [pdf] [code on github] [fastforward] [See the results here] [bibtex]

    Locally Scale-invariant Convolutional Neural Network
    Angjoo Kanazawa, Abhishek Sharma, David W. Jacobs
    Deep Learning and Representation Learning Workshop: NIPS 2014.
    [pdf] [code on github] [bibtex]

    Affordance of Object Parts from Geometric Features
    Austin Myers, Angjoo Kanazawa, Cornelia Fermuller, Yiannis Aloimonos
    RGB-D: Advanced Reasoning with Depth Cameras: RSS 2014
    [pdf] [bibtex] [Part Affordance Dataset] [bibtex]

    Dog Breed Classification Using Part Localization
    Jiongxin Liu, Angjoo Kanazawa, Peter Belhumeur, David W. Jacobs
    European Conference on Computer Vision (ECCV), Oct. 2012.
    [pdf] [slides] [bibtex]
    try our iPhone app: Dogsnap !
    Columbia dogs with parts dataset used in the paper: zip file (2.43GB)

    • 133 breeds recognized by the American Kennel Club

    • 8,351 images of dogs from Google image search, Image-net, and Flickr.

    • 8 part locations annotated for each image

    Thesis

    Single-View 3D Reconstruction of Animals
    Angjoo Kanazawa
    Doctoral Thesis, University of Maryland, August 2017
    [pdf] [slides]

    Teaching

    Misc