Surface Normals Estimation

32 papers with code • 7 benchmarks • 11 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.

PolyMaX: General Dense Prediction with Mask Transformer

google-research/deeplab2 9 Nov 2023

Despite this shift, methods based on the per-pixel prediction paradigm still dominate the benchmarks on the other dense prediction tasks that require continuous outputs, such as depth estimation and surface normal prediction.

980
09 Nov 2023

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

StanfordORB/Stanford-ORB NeurIPS 2023

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.

48
24 Oct 2023

MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning

martianxiu/MSECNet 4 Aug 2023

MSECNet consists of a backbone network and a multi-scale edge conditioning (MSEC) stream.

16
04 Aug 2023

MIMIC: Masked Image Modeling with Image Correspondences

raivnlab/mimic 27 Jun 2023

We train multiple models with different masked image modeling objectives to showcase the following findings: Representations trained on our automatically generated MIMIC-3M outperform those learned from expensive crowdsourced datasets (ImageNet-1K) and those learned from synthetic environments (MULTIVIEW-HABITAT) on two dense geometric tasks: depth estimation on NYUv2 (1. 7%), and surface normals estimation on Taskonomy (2. 05%).

15
27 Jun 2023

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.

272
13 Apr 2023

NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination

FuxiComputerVision/Nefii CVPR 2023

Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images.

19
29 Mar 2023

NeAF: Learning Neural Angle Fields for Point Normal Estimation

lisj575/NeAF 30 Nov 2022

To resolve these issues, we propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system, which is dubbed as Neural Angle Fields (NeAF).

31
30 Nov 2022

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

leoqli/hsurf-net 13 Oct 2022

To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.

30
13 Oct 2022

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

uestcjay/graphfit 23 Jul 2022

We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds.

26
23 Jul 2022

Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising

NVlabs/nvdiffrecmc 7 Jun 2022

Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging.

345
07 Jun 2022