Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Surface Normals Estimation

3260 papers • 126 benchmarks • 313 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.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in surface-normals-estimation-7

Trend

Dataset

Best Model

Actions

PCPNet

PCPNet

Stanford-ORB

Stanford-ORB

NYU Depth v2

NYU Depth v2

Libraries

i

Use these libraries to find surface-normals-estimation-7 models and implementations

Datasets

ScanNet

NYUv2

PASCAL Context

Taskonomy

GRIT

Stanford-ORB

Subtasks

No subtasks available.

Most implemented papers

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres

Shuai Liao, E. Gavves, Cees G. M. Snoek•Tue Apr 09 2019

By introducing a spherical exponential mapping on n-spheres at the regression output, this work obtains well-behaved gradients, leading to stable training and shows how the spherical regression can be utilized for several computer vision challenges, specifically viewpoint estimation, surface normal estimation and 3D rotation estimation.

71

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

ScanNetV2

ScanNetV2

Taskonomy

Taskonomy

NYU-Depth V2 Surface Normals

NYU-Depth V2 Surface Normals

PASCAL Context

PASCAL Context

3D Ken Burns Dataset

3D Ken Burns Dataset

SuperCaustics

Pano3D

TransProteus

0

Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations

I. Reid, Chunhua Shen, T. Drummond, Vladimir Nekrasov, Thanuja Dharmasiri, Andrew Spek•Wed Sep 12 2018

This work adapts a recently proposed real-time semantic segmentation network, making changes to further reduce the number of floating point operations, and incorporates the raw predictions of the network into the SemanticFusion framework for dense 3D semantic reconstruction of the scene.

155 0

Deep Iterative Surface Normal Estimation

Jonathan Masci, J. E. Lenssen, Christian Osendorfer•Sun Apr 14 2019

This paper presents an end-to-end differentiable algorithm for robust and detail-preserving surface normal estimation on unstructured point-clouds. We utilize graph neural networks to iteratively parameterize an adaptive anisotropic kernel that produces point weights for weighted least-squares plane fitting in local neighborhoods. The approach retains the interpretability and efficiency of traditional sequential plane fitting while benefiting from adaptation to data set statistics through deep learning. 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. Contrary to previous deep learning methods, the proposed approach does not require any hand-crafted features or preprocessing. It improves on the state-of-the-art results while being more than two orders of magnitude faster and more parameter efficient.

82 0

$360^o$ Surface Regression with a Hyper-Sphere Loss

P. Daras, N. Zioulis, D. Zarpalas, Antonis Karakottas, V. Gkitsas, Stamatis Samaras, Dimitrios Ataloglou•Sun Sep 15 2019

This work addresses the unavailability of sufficient ground truth normal data, by leveraging existing 3D datasets and remodelling them via rendering and training a deep convolutional neural network on the task of monocular 360 surface estimation.

7 0

Extracting Triangular 3D Models, Materials, and Lighting From Images

S. Fidler, Alex Evans, T. Müller, Wenzheng Chen, Jun Gao, Jacob Munkberg, J. Hasselgren, Tianchang Shen•Tue Nov 23 2021

This work outputs triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified, and introduces a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting.

460 0

iDisc: Internal Discretization for Monocular Depth Estimation

F. Yu, Christos Sakaridis, Luigi Piccinelli•Wed Apr 12 2023

iDisc, a new module, implements a continuous-discrete-continuous bottleneck to learn internal discretized representations without supervision, and 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.

113 0

Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks

M. Lindenbaum, Yizhak Ben-Shabat, A. Fischer•Sun Dec 02 2018

The Nesti-Net method builds on a new local point cloud representation which consists of multi-scale point statistics (MuPS), estimated on a local coarse Gaussian grid, which is a suitable input to a CNN architecture.

109 0

Creative Flow+ Dataset

S. Fidler, Maria Shugrina, Z. Liang, Amlan Kar, Jiaman Li, Angad Singh, Karan Singh•Fri May 31 2019

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. Our dataset includes 3000 animated sequences rendered using styles randomly selected from 40 textured line styles and 38 shading styles, spanning the range between flat cartoon fill and wildly sketchy shading. Our dataset includes 124K+ train set frames and 10K test set frames rendered at 1500x1500 resolution, far surpassing the largest available optical flow datasets in size. While modern techniques for tasks such as optical flow estimation achieve impressive performance on realistic images and video, today there is no way to gauge their performance on non-photorealistic images. Creative Flow+ poses a new challenge to generalize real-world Computer Vision to messy stylized content. We show that learning-based optical flow methods fail to generalize to this data and struggle to compete with classical approaches, and invite new research in this area. Our dataset and a new optical flow benchmark will be publicly available at: www.cs.toronto.edu/creativeflow/. We further release the complete dataset creation pipeline, allowing the community to generate and stylize their own data on demand.

23 0

Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction

K. Murphy, Karthik Raveendran, Irfan Essa, Steven Hickson, A. Fathi•Sat Jun 15 2019

4 insights are proposed that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image and are demonstrated consistently improved state of the art results on several datasets.

17 0

Adding a benchmark result helps the community track progress.

Surface Normals Estimation | State-of-the-Art