LRM: Large Reconstruction Model for Single Image to 3D
2023
Online
report
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs, including real-world in-the-wild captures and images created by generative models. Video demos and interactable 3D meshes can be found on our LRM project webpage: https://yiconghong.me/LRM.
Comment: ICLR 2024
Titel: |
LRM: Large Reconstruction Model for Single Image to 3D
|
---|---|
Autor/in / Beteiligte Person: | Hong, Yicong ; Zhang, Kai ; Gu, Jiuxiang ; Bi, Sai ; Zhou, Yang ; Liu, Difan ; Liu, Feng ; Sunkavalli, Kalyan ; Bui, Trung ; Tan, Hao |
Link: | |
Veröffentlichung: | 2023 |
Medientyp: | report |
Schlagwort: |
|
Sonstiges: |
|