MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916465944297472 |
|---|---|
| author | Zhao, Wang Liu, Jiachen Zhang, Sheng Li, Yishu Chen, Sili Huang, Sharon X Liu, Yong-Jin Guo, Hengkai |
| author_facet | Zhao, Wang Liu, Jiachen Zhang, Sheng Li, Yishu Chen, Sili Huang, Sharon X Liu, Yong-Jin Guo, Hengkai |
| contents | This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and establishes a plane reconstruction pipeline based on monocular geometric cues, resulting in accurate, robust and scalable 3D plane detection and reconstruction in the wild. Specifically, we first leverage large-scale pre-trained neural networks to obtain the depth and surface normals from a single image. These monocular geometric cues are then incorporated into a proximity-guided RANSAC framework to sequentially fit each plane instance. We exploit effective 3D point proximity and model such proximity via a graph within RANSAC to guide the plane fitting from noisy monocular depths, followed by image-level multi-plane joint optimization to improve the consistency among all plane instances. We further design a simple but effective pipeline to extend this single-view solution to sparse-view 3D plane reconstruction. Extensive experiments on a list of datasets demonstrate our superior zero-shot generalizability over baselines, achieving state-of-the-art plane reconstruction performance in a transferring setting. Our code is available at https://github.com/thuzhaowang/MonoPlane . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01226 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction Zhao, Wang Liu, Jiachen Zhang, Sheng Li, Yishu Chen, Sili Huang, Sharon X Liu, Yong-Jin Guo, Hengkai Computer Vision and Pattern Recognition Robotics This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and establishes a plane reconstruction pipeline based on monocular geometric cues, resulting in accurate, robust and scalable 3D plane detection and reconstruction in the wild. Specifically, we first leverage large-scale pre-trained neural networks to obtain the depth and surface normals from a single image. These monocular geometric cues are then incorporated into a proximity-guided RANSAC framework to sequentially fit each plane instance. We exploit effective 3D point proximity and model such proximity via a graph within RANSAC to guide the plane fitting from noisy monocular depths, followed by image-level multi-plane joint optimization to improve the consistency among all plane instances. We further design a simple but effective pipeline to extend this single-view solution to sparse-view 3D plane reconstruction. Extensive experiments on a list of datasets demonstrate our superior zero-shot generalizability over baselines, achieving state-of-the-art plane reconstruction performance in a transferring setting. Our code is available at https://github.com/thuzhaowang/MonoPlane . |
| title | MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2411.01226 |