Mirror3D: Depth Refinement for Mirror Surfaces
| Autor: | Jiaqi Tan, Angel X. Chang, Weijie Lin, Manolis Savva |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) 3D reconstruction Computer Science - Computer Vision and Pattern Recognition Context (language use) 02 engineering and technology 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Prediction methods 0202 electrical engineering electronic engineering information engineering RGB color model 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Mirror plane Surface reconstruction Surface depth |
| Zdroj: | CVPR |
| Popis: | Despite recent progress in depth sensing and 3D reconstruction, mirror surfaces are a significant source of errors. To address this problem, we create the Mirror3D dataset: a 3D mirror plane dataset based on three RGBD datasets (Matterport3D, NYUv2 and ScanNet) containing 7,011 mirror instance masks and 3D planes. We then develop Mirror3DNet: a module that refines raw sensor depth or estimated depth to correct errors on mirror surfaces. Our key idea is to estimate the 3D mirror plane based on RGB input and surrounding depth context, and use this estimate to directly regress mirror surface depth. Our experiments show that Mirror3DNet significantly mitigates errors from a variety of input depth data, including raw sensor depth and depth estimation or completion methods. Paper presented at CVPR 2021. For code, data and pretrained models, see https://3dlg-hcvc.github.io/mirror3d/ |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|