Understand
If a picture is worth thousand words, a moving 3d shape must be worth a million.
- We build upon the success of recent generative methods that create images fitting the semantics of a text prompt, and extend it to the controlled generation of 3d objects.
- We present a novel algorithm for the creation of textured 3d meshes, controlled by text prompts.
- Our method creates aesthetically pleasing high resolution articulated 3d meshes, and opens new possibilities for automation and AI control of 3d assets.
Built on
Differentiable image parameterizations
Alexander Mordvintsev, Nicola Pezzotti, Ludwig Schubert, and Chris Olah · 2018
Earlier work this paper cites.
Expressive body capture: 3d hands, face, and body from a single image
Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, and Michael J. Black · 2019
Earlier work this paper cites.
Accelerating 3d deep learning with pytorch3d
Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari · 2020
Earlier work this paper cites.
Similar
Learning to transfer texture from clothing images to 3d humans
Aymen Mir, Thiemo Alldieck, and Gerard Pons-Moll · 2020
Cited alongside, same era.
Learning transferable visual models from natural language supervision, 2021
Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever · 2021
Cited alongside, same era.
Then
Thoughts on deepdaze, bigsleep, and aleph2image
Ryan Murdock https://twitter.com/advadnoun · 2021
Closest in time.
Putting nerf on a diet: Semantically consistent few-shot view synthesis, 2021
Ajay Jain, Matthew Tancik, and Pieter Abbeel · 2021
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…