PlaneFormers: From Sparse View Planes to 3D Reconstruction
dc.contributor.author | Agarwala, Samir | |
dc.contributor.author | Jin, Linyi | |
dc.contributor.author | Rockwell, Chris | |
dc.contributor.author | Fouhey, David | |
dc.contributor.advisor | Fouhey, David | |
dc.date.accessioned | 2023-05-26T17:56:08Z | |
dc.date.available | 2023-05-26T17:56:08Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/176738 | |
dc.description.abstract | Indoor scenes such as rooms, kitchens and other areas of houses are pre-dominantly composed of planar surfaces. These surfaces may thus be used to generate high-quality scene reconstructions. Previous approaches in this domain are generally optimization-based and use an expensive bundle adjustment step. We propose the PlaneFormer, a transformer-based approach, that takes in 3D-aware plane tokens as inputs and can reconstruct scenes using planar surfaces. Our experiments show that our method outperforms baselines on most metrics, can be extended reasonably to multiple views and requires several 3D-specific choices to perform effectively on the task. | |
dc.subject | Computer Vision | |
dc.subject | Scene Reconstruction | |
dc.subject | Sparse Views | |
dc.title | PlaneFormers: From Sparse View Planes to 3D Reconstruction | |
dc.type | Project | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.peerreviewed | NA | |
dc.contributor.affiliationum | Computer Science and Engineering | |
dc.contributor.affiliationumcampus | Ann Arbor | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/176738/1/Honors_Thesis_PlaneFormers_-_Samir_Agarwala.pdf | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/176738/2/Honors_Poster_PlaneFormers_-_Samir_Agarwala.pdf | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/176738/3/Honors_Video_PlaneFormers_-_Samir_Agarwala.mp4 | |
dc.identifier.doi | https://dx.doi.org/10.7302/7587 | |
dc.working.doi | 10.7302/7587 | en |
dc.owningcollname | Honors Program, The College of Engineering |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.