We study the emerging research problem of connecting natural language describing objects and scenes to 3D data representations of the objects and scenes. We address resolving textual references of objects to 3D localizations of those objects, dense captioning of 3D scenes, and unified approaches that can both localize and describe objects in 3D scenes by leveraging a speaker-listener model. full report …
Scientific Report on TUM-IAS Fellowship 2020
We in the Visual Computing Focus Group are research enthusiasts pushing the state of the art at the intersection of computer vision, graphics, and machine learning. Our research mission is to obtain high-quality digital models of the real world, which include detailed geometry, surface texture, and material in both static and dynamic environments. full report
Short CV
Selected Awards
Research Interests
Selected Publications
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 https://arxiv.org/pdf/2003.08515.pdf
Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings Kevin Chen, Christopher B. Choy, Manolis Savva, Angel X. Chang, Thomas Funkhouser, Silvio Savarese ACCV 2018 https://arxiv.org/pdf/1803.08495.pdf
ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner CVPR 2017 https://arxiv.org/pdf/1702.04405.pdf
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 2015 https://arxiv.org/pdf/1512.03012v1.pdf
Chen, Dave Zhenyu; Hu, Ronghang; Chen, Xinlei; Nießner, Matthias; Chang, Angel X.: UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding. , 2022 mehr…BibTeX
Volltext (
DOI
)
2021
Chen, Dave Zhenyu; Wu, Qirui; Nießner, Matthias; Chang, Angel X.: D3Net: A Speaker-Listener Architecture for Semi-supervised Dense Captioning and Visual Grounding in RGB-D Scans. , 2021 mehr…BibTeX
Volltext (
DOI
)
2020
Chen, Dave Zhenyu; Chang, Angel X.; Nießner, Matthias: ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language. 2020 mehr…BibTeX
Chen, Dave Zhenyu; Gholami, Ali; Nießner, Matthias; Chang, Angel X.: Scan2Cap: Context-aware Dense Captioning in RGB-D Scans. 2020 mehr…BibTeX