Single Image 3D Interpreter Network
Understanding 3D object structure from a single image is an important but difficult task in computer vision, mostly due to the lack of 3D object annotations in real images. Previous work tackles this problem by either solving an optimization task given 2D keypoint positions, or training on synthetic...
Main Authors: | Tian, Yuandong, Wu, Jiajun, Xue, Tianfan, Lim, Joseph Jaewhan, Tenenbaum, Joshua B, Torralba, Antonio, Freeman, William T. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Language: | en_US |
Published: |
Springer
2018
|
Online Access: | http://hdl.handle.net/1721.1/114448 https://orcid.org/0000-0002-4176-343X https://orcid.org/0000-0001-5031-6618 https://orcid.org/0000-0002-2476-6428 https://orcid.org/0000-0002-1925-2035 https://orcid.org/0000-0003-4915-0256 https://orcid.org/0000-0002-2231-7995 |
Similar Items
-
3D Interpreter Networks for Viewer-Centered Wireframe Modeling
by: Wu, Jiajun, et al.
Published: (2020) -
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
by: Sun, Xingyuan, et al.
Published: (2022) -
Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling
by: Wu, Jiajun, et al.
Published: (2017) -
MarrNet: 3D shape reconstruction via 2.5D sketches
by: Wu, Jiajun, et al.
Published: (2020) -
Galileo: Perceiving physical object properties by integrating a physics engine with deep learning
by: Yildirim, Ilker, et al.
Published: (2018)