Surface Normal Estimation
38 papers with code • 2 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Surface Normal Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
NYUv2
GRIT
3D Ken Burns Dataset
FutureHouse
Most implemented papers
Pixel-wise Attentional Gating for Parsimonious Pixel Labeling
To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each layer of a deep convolutional network.
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
xjqi/GeoNet
•
•
CVPR 2018
In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image.
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection
vita-epfl/rock-pytorch
•
•
NeurIPS 2018
Multi-Task Learning (MTL) is appealing for deep learning regularization.
FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
In this work, we introduce the novel problem of identifying dense canonical 3D coordinate frames from a single RGB image.
Deep Surface Normal Estimation with Hierarchical RGB-D Fusion
jzengust/RGBD2Normal
•
•
CVPR 2019
The growing availability of commodity RGB-D cameras has boosted the applications in the field of scene understanding.
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
HKBU-HPML/IRS
•
•
Besides, we present DTN-Net, a two-stage deep model for surface normal estimation.
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
koutilya40192/SharinGAN
•
•
CVPR 2020
Ideally, this results in images from two domains that present shared information to the primary network.
Surface Normal Estimation of Tilted Images via Spatial Rectifier
MARSLab-UMN/TiltedImageSurfaceNormal
•
•
ECCV 2020
Our two main hypotheses are: (1) visual scene layout is indicative of the gravity direction; and (2) not all surfaces are equally represented by a learned estimator due to the structured distribution of the training data, thus, there exists a transformation for each tilted image that is more responsive to the learned estimator than others.
HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures
We present HoliCity, a city-scale 3D dataset with rich structural information.
Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
ygjwd12345/TransDepth
•
•
ICCV 2021
While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution operation.
