Angel Xuan Chang

I am an Assistant Professor at Simon Fraser University. Prior to this, I was a visiting research scientist at Facebook AI Research and a research scientist at Eloquent Labs working on dialogue. I received my Ph.D. in Computer Science from Stanford, where I was part of the Natural Language Processing Group and advised by Chris Manning. My research focuses on connecting language to 3D representations of shapes and scenes and grounding of language for embodied agents in indoor environments. I have worked on methods for synthesizing 3D scenes and shapes from natural language, and various datasets for 3D scene understanding. In general, I am interested in the semantics of shapes and scenes, the representation and acquisition of common sense knowledge, and reasoning using probabilistic models. Some of my other interests include drawing and dance.

News

July 2023 - Three papers accepted at ICCV 2023. Congratulations to
- Yiming and ZeMing for their work on Multi3DRefer, a extension of 3D visual grounding to multiple objects
- Dave for his work on UniT3D, a unified transformer model for 3D visual grounding and captioning
- Enrico and Tommaso for their work on proximity-aware tasks for social navigation
July 24, 2023 - Lecture on natural language processing at Invent the Future: AI Scholars Program at Simon Fraser University
July 13, 2023 - Talk on Connecting 3D and Language at Seoul National University.
July 4, 2023 - Talk on Connecting 3D and Language at University of Padova.
July 1, 2023 - Tutorial on Language and 3D at SGP 2023.

More...

      angelx-{at}-sfu-[dot]-ca
    

Assistant Professor
School of Computing Science
Simon Fraser University
GrUVi Lab | SFU NatLang | SFU AI/ML
Canada CIFAR AI Chair (Amii)
TUM-IAS Hans Fischer Fellow
Google Scholar

Recent Papers

HomeRobot: Open Vocabulary Mobile Manipulation

Sriram Yenamandra, Arun Ramachandran, Karmesh Yadav, Austin Wang, Mukul Khanna, Theo Gervet, Tsung-Yen Yang, Vidhi Jain, Alexander William Clegg, John Turner, Zsolt Kira, Manolis Savva, Angel X. Chang, Devendra Chaplot, Dhruv Batra, Roozbeh Mottaghi, Yonatan Bisk, Chris Paxton
arXiv:2306.11565 [cs.RO, cs.CV], June 2023
pdf | code | challenge | webpage

Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation

Mukul Khanna, Yongsen Mao, Hanxiao (Shawn) Jiang, Sanjay Haresh, Brennan Shacklett, Dhruv Batra, Alexander William Clegg, Eric Undersander, Angel X. Chang, Manolis Savva
arXiv:2306.11290 [cs.CV], June 2023
pdf | code | data | webpage

Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance

Supriya Pandhre, Angel X. Chang, Manolis Savva
CRV 2023
pdf

Reduce, Reuse, Recycle: Modular Multi-Object Navigation

Sonia Raychaudhuri, Tommaso Campari, Unnat Jain, Manolis Savva, Angel X. Chang
arXiv:2304.03696 [cs.RO, cs.CV], April 2023
pdf | code | webpage

OPDMulti: Openable Part Detection for Multiple Objects

Xiaohao Sun, Hanxiao (Shawn) Jiang, Manolis Savva, Angel X. Chang
arXiv:2303.14087 [cs.CV], March 2023
pdf | code | webpage

More...

Research Themes

Grounding language to 3D
Language based content creation
Embodied AI
Simulation platforms
Articulated objects for interactive environments
Large-scale datasets for 3D deep learning
3D scene understanding and generation

Grounding language to 3D

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

Dave Zhenyu Chen, Ronghang Hu, Xinlei Chen, Matthias Nießner, Angel X. Chang
arXiv:2212.00836 [cs.CV], December 2022
pdf | webpage

D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

Dave Zhenyu Chen, Qirui Wu, Matthias Nießner, Angel X. Chang
ECCV 2022
pdf | code | webpage

TriCoLo: Trimodal Contrastive Loss for fine-grained Text to Shape Retrieval

Yue Ruan, Han-Hung Lee, Ke Zhang, Angel X. Chang
arXiv:2201.07366 [cs.CV], January 2022
pdf | code | webpage

Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Dave Zhenyu Chen, Ali Gholami, Matthias Nießner, Angel X. Chang
CVPR 2021
pdf | code | webpage

ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

Dave Zhenyu Chen, Angel X. Chang, Matthias Nießner
ECCV 2020
pdf | code | benchmark | webpage

Language based content creation

Understanding Pure CLIP Guidance for Voxel Grid NeRF Models

Han-Hung Lee, Angel X. Chang
arXiv:2201.07366 [cs.CV], September 2022
pdf | code | webpage

Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

Kevin Chen, Christopher B. Choy, Manolis Savva, Angel X. Chang, Thomas Funkhouser, Silvio Savarese
Proceedings of ACCV 2018 (oral), arXiv:1803.08495 [cs.CV]
pdf | code | webpage

Text to 3D Scene Generation with Rich Lexical Grounding

Angel X. Chang, Will Monroe, Manolis Savva, Christopher Potts, Christopher D. Manning
Proceedings of ACL 2015
pdf | bib | webpage

Learning Spatial Knowledge for Text to 3D Scene Generation

Angel X. Chang, Manolis Savva, Christopher D. Manning
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014)
pdf | bib | webpage

Embodied AI

HomeRobot: Open Vocabulary Mobile Manipulation

Reduce, Reuse, Recycle: Modular Multi-Object Navigation

Sonia Raychaudhuri, Tommaso Campari, Unnat Jain, Manolis Savva, Angel X. Chang
arXiv:2304.03696 [cs.RO, cs.CV], April 2023
pdf | code | webpage

Exploiting Proximity-Aware Tasks for Embodied Social Navigation

Enrico Cancelli, Tommaso Campari, Luciano Serafini, Angel X. Chang, Lamberto Ballan
arXiv:2212.00767 [cs.CV], December 2022
pdf

Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments

Sonia Raychaudhuri, Shivansh Patel, Saim Wani, Unnat Jain, Angel X. Chang
EMNLP 2021 (short)
pdf | code | webpage

Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents

Shivansh Patel, Saim Wani, Unnat Jain, Alexander Schwing, Svetlana Lazebnik, Manolis Savva, Angel X. Chang
ICCV 2021
pdf | code | webpage

Rearrangement: A Challenge for Embodied AI

Dhruv Batra, Angel X. Chang, Sonia Chernova, Andrew J. Davison, Jia Deng, Vladlen Koltun, Sergey Levine, Jitendra Malik, Igor Mordatch, Roozbeh Mottaghi, Manolis Savva, Hao Su
arXiv:2011.01975 [cs.AI], November 2020
pdf

Multi-ON: Benchmarking Semantic Map Memory using Multi-Object Navigation

Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang, Manolis Savva
NeurIPS 2020
pdf | code | webpage

On evaluation of embodied navigation agents

Peter Anderson, Angel X. Chang, Devendra Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, Amir R. Zamir
arXiv:1807.06757 [cs.AI], July 2018
pdf

Simulation platforms

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

Andrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Chaplot, Oleksandr Maksymets, Aaron Gokaslan, Vladimír Vondrus, Sameer Dharur, Franziska Meier, Wojciech Galuba, Angel X. Chang, Zsolt Kira, Vladlen Koltun, Jitendra Malik, Manolis Savva, Dhruv Batra
NeurIPS 2021
pdf | code | post

SAPIEN: a SimulAted Part-based Interactive ENvironment

Fanbo Xiang, Yuzhe Qin, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao (Shawn) Jiang, Yifu Yuan, He Wang, Li Yi, Angel X. Chang, Leonidas Guibas, Hao Su
CVPR 2020
pdf | webpage

MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments

Manolis Savva, Angel X. Chang, Alexey Dosovitskiy, Thomas Funkhouser, Vladlen Koltun
arXiv:1712.03931 [cs.LG]
pdf | code | video | webpage

Articulated objects for interactive environments

OPDMulti: Openable Part Detection for Multiple Objects

Xiaohao Sun, Hanxiao (Shawn) Jiang, Manolis Savva, Angel X. Chang
arXiv:2303.14087 [cs.CV], March 2023
pdf | code | webpage

MultiScan: Scalable RGBD scanning for 3D environments with articulated objects

Yongsen Mao, Yiming Zhang, Hanxiao (Shawn) Jiang, Angel X. Chang, Manolis Savva
NeurIPS 2022
pdf | code | webpage

Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges

Sanjay Haresh, Xiaohao Sun, Hanxiao (Shawn) Jiang, Angel X. Chang, Manolis Savva
3DV 2022
pdf | code | webpage

OPD: Single-view 3D Openable Part Detection

Hanxiao (Shawn) Jiang, Yongsen Mao, Manolis Savva, Angel X. Chang
ECCV 2022
pdf | code | webpage

Motion Annotation Programs: A Scalable Approach to Annotating Kinematic Articulations in Large 3D Shape Collections

Xianghao Xu, David Charatan, Sonia Raychaudhuri, Hanxiao (Shawn) Jiang, Mae Heitmann, Vladmir Kim, Siddhartha Chaudhuri, Manolis Savva, Angel X. Chang, Daniel Ritchie
3DV 2020
pdf | code | demo | webpage

Large-scale datasets for 3D deep learning

Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation

Habitat-Matterport 3D Semantics Dataset

Karmesh Yadav, Ram Ramrakhya, Santhosh K. Ramakrishnan, Theo Gervet, John Turner, Aaron Gokaslan, Noah Maestre, Angel X. Chang, Dhruv Batra, Manolis Savva, Alexander William Clegg, Devendra Chaplot
CVPR 2023
pdf | webpage

Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI

Santhosh K. Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets, Alexander Clegg, John Turner, Eric Undersander, Wojciech Galuba, Andrew Westbury, Angel X. Chang, Manolis Savva, Yili Zhao, Dhruv Batra
NeurIPS Datasets and Benchmarks Track 2021
pdf | webpage

Mirror3D: Depth Refinement for Mirror Surfaces

Jiaqi Tan, Weijie (Lewis) Lin, Angel X. Chang, Manolis Savva
CVPR 2021
pdf | code | webpage

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

Kaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi, Subarna Tripathi, Leonidas Guibas, Hao Su
CVPR 2019, arXiv:1812.02713 [cs.CV]
pdf | video | webpage

Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

Armen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, Matthias Nießner
CVPR 2019 (oral), arXiv:1811.11187 [cs.CV]
pdf | code | video | benchmark

Matterport3D: Learning from RGB-D Data in Indoor Environments

Angel X. Chang, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Nießner, Manolis Savva, Shuran Song, Andy Zeng, Yinda Zhang
Proceedings of 3DV 2017, arXiv:1709.06158 [cs.CV]
pdf | code | webpage

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner
Proceedings of CVPR 2017 (spotlight), arXiv:1702.04405 [cs.CV]
pdf | code | video | benchmark | webpage

ShapeNet: An Information-Rich 3D Model Repository

Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, Fisher Yu
arXiv:1512.03012 [cs.GR], Dec 2015
pdf | bib | code | webpage

3D scene understanding and generation

Roominoes: Learning to Assemble 3D Rooms into Floor Plans

Kai Wang, Xianghao Xu, Leon Lei, Selena Ling, Natalie Lindsay, Angel X. Chang, Manolis Savva, Daniel Ritchie
SGP 2021
pdf | video

Plan2Scene: Converting Floorplans to 3D Scenes

Madhawa Vidanapathirana, Qirui Wu, Yasutaka Furukawa, Angel X. Chang, Manolis Savva
CVPR 2021
pdf | code | webpage

PlanIT: Planning and Instantiating Indoor Scenes with Relation Graph and Spatial Prior Networks

Kai Wang, Yu-An Lin, Ben Weissmann, Manolis Savva, Angel X. Chang, Daniel Ritchie
SIGGRAPH 2019
pdf | code

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

Yifei Shi, Angel X. Chang, Zhelun Wu, Manolis Savva, Kai Xu
CVPR 2019, arXiv:1903.03757 [cs.CV]
pdf | code | webpage

Deep Convolutional Priors for Indoor Scene Synthesis

Kai Wang, Manolis Savva, Angel X. Chang, Daniel Ritchie
SIGGRAPH 2018
pdf | code

Semantic Scene Completion from a Single Depth Image

Shuran Song, Fisher Yu, Andy Zeng, Angel X. Chang, Manolis Savva, Thomas Funkhouser
Proceedings of CVPR 2017 (oral), arXiv:1611.08974 [cs.CV]
pdf | webpage