Surface Normals Estimation
33 papers with code • 8 benchmarks • 12 datasets
Surface normal estimation deals with the task of predicting the surface orientation of the objects present inside a scene. Refer to Designing Deep Networks for Surface Normal Estimation (Wang et al.) to get a good overview of several design choices that led to the development of a CNN-based surface normal estimator.
Benchmarks
These leaderboards are used to track progress in Surface Normals Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
ScanNet
NYUv2
PASCAL Context
Taskonomy
IBims-1
GRIT
Stanford-ORB
3D Ken Burns Dataset
Pano3D
SuperCaustics
Most implemented papers
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
DrSleep/multi-task-refinenet
•
•
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
BlenderProc
BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.
Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
leoshine/Spherical_Regression
•
•
CVPR 2019
We observe many continuous output problems in computer vision are naturally contained in closed geometrical manifolds, like the Euler angles in viewpoint estimation or the normals in surface normal estimation.
Deep Iterative Surface Normal Estimation
nnaisense/deep-iterative-surface-normal-estimation
•
•
CVPR 2020
This results in a state-of-the-art surface normal estimator that is robust to noise, outliers and point density variation, preserves sharp features through anisotropic kernels and equivariance through a local quaternion-based spatial transformer.
$360^o$ Surface Regression with a Hyper-Sphere Loss
VCL3D/SphericalViewSynthesis
•
•
We present a dataset of $360^o$ images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation.
Extracting Triangular 3D Models, Materials, and Lighting From Images
NVlabs/nvdiffrec
•
•
CVPR 2022
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
iDisc: Internal Discretization for Monocular Depth Estimation
SysCV/idisc
•
•
CVPR 2023
Our method sets the new state of the art with significant improvements on NYU-Depth v2 and KITTI, outperforming all published methods on the official KITTI benchmark.
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks
sitzikbs/Nesti-Net
•
•
CVPR 2019
In this paper, we propose a normal estimation method for unstructured 3D point clouds.
Creative Flow+ Dataset
We present the Creative Flow+ Dataset, the first diverse multi-style artistic video dataset richly labeled with per-pixel optical flow, occlusions, correspondences, segmentation labels, normals, and depth.
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image.
