paper-with-me

홈 › Papers

Designing Deep Networks for Surface Normal Estimation

2014-11-18 · CVPR 2015 6 · Xiaolong Wang, David F. Fouhey, Abhinav Gupta

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture we should use? We propose to build upon the decades of hard work in 3D scene understanding, to design new CNN architecture for the task of surface normal estimation. We show by incorporating several constraints (man-made, manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning.

📄 PDF Abstract BibTeX arXiv:1411.4958

Code (0)

등록된 구현이 없습니다.

Tasks

Scene UnderstandingSurface Normal Estimation

Similar Papers 제목 키워드 기반

GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

2018-06-01 · CVPR 2018 6 · Xiaojuan Qi, Renjie Liao, Zhengzhe Liu, Raquel Urtasun 외

In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image. Building on top of two-stream CNNs, our GeoNet incorporates geometric relation between dep…

Depth EstimationSurface Normal Estimation

Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps

2022-09-17 · Saed Moradi, Alireza Memarmoghadam, Denis Laurendeau

This paper proposes a fast and accurate surface normal estimation method which can be directly used on depth maps (organized point clouds). The surface normal estimation process is formulated as a closed-form expression.…

Surface Normal Estimation

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

2023-03-30 · CVPR 2023 1 · Hang Du, Xuejun Yan, Jingjing Wang, Di Xie 외

Most existing approaches for point cloud normal estimation aim to locally fit a geometric surface and calculate the normal from the fitted surface. Recently, learning-based methods have adopted a routine of predicting po…

FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash Images

2026-08-26 · Ruiyang Chen, Feiran Li, Heng Guo, Zhanyu Ma arxiv

High-quality surface normal estimation is preferred for detailed surface shape recovery and image editing. Existing single image-based methods, though being a practical setup, often struggle to recover fine surface detai…

Image Editing

IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

2022-10-07 · Gwangbin Bae, Ignas Budvytis, Roberto Cipolla

Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from the output of depth estimation methods …

Monocular Depth Estimation