SOTAVerified

Surface Normals Estimation

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.

Papers

Showing 139 of 39 papers

TitleStatusHype
Learning from the Giants: A Practical Approach to Underwater Depth and Surface Normals Estimation0
Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkCode4
PolyMaX: General Dense Prediction with Mask TransformerCode0
Stanford-ORB: A Real-World 3D Object Inverse Rendering BenchmarkCode1
Large-scale Monocular Depth Estimation in the Wild0
MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge ConditioningCode1
MIMIC: Masked Image Modeling with Image CorrespondencesCode1
Neural-PBIR Reconstruction of Shape, Material, and Illumination0
iDisc: Internal Discretization for Monocular Depth EstimationCode3
NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect IlluminationCode1
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision0
NeAF: Learning Neural Angle Fields for Point Normal EstimationCode1
HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper SurfacesCode1
GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal EstimationCode1
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingCode2
GRIT: General Robust Image Task BenchmarkCode1
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
Extracting Triangular 3D Models, Materials, and Lighting From ImagesCode2
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal EstimationCode1
AdaFit: Rethinking Learning-based Normal Estimation on Point CloudsCode1
NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown IlluminationCode1
PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting0
NeRD: Neural Reflectance Decomposition from Image CollectionsCode1
How Well Do Self-Supervised Models Transfer?Code1
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation0
AI Playground: Unreal Engine-based Data Ablation Tool for Deep LearningCode1
Robust Learning Through Cross-Task ConsistencyCode1
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry EstimationCode1
Robust Learning Through Cross-Task ConsistencyCode1
DeepFit: 3D Surface Fitting via Neural Network Weighted Least SquaresCode1
BlenderProcCode2
ClearGrasp: 3D Shape Estimation of Transparent Objects for ManipulationCode0
360^o Surface Regression with a Hyper-Sphere LossCode0
Floors are Flat: Leveraging Semantics for Real-Time Surface Normal PredictionCode0
Creative Flow+ DatasetCode0
Deep Iterative Surface Normal EstimationCode0
Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-SpheresCode0
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural NetworksCode0
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric AnnotationsCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Nesti-NetRMSE 12.41Unverified
2Iter-NetRMSE 11.84Unverified
3DeepFitRMSE 11.8Unverified
4AdaFitRMSE 10.76Unverified
5GraphFitRMSE 10.26Unverified
6NeAFRMSE 10.22Unverified
7HsurfRMSE 10.11Unverified
8MSECNetRMSE 9.76Unverified
#ModelMetricClaimedVerifiedStatus
1NeRFactorCosine Distance0.29Unverified
2NeRDCosine Distance0.28Unverified
3PhySGCosine Distance0.17Unverified
4InvRenderCosine Distance0.06Unverified
5NVDiffRecCosine Distance0.06Unverified
6Neural-PBIRCosine Distance0.06Unverified
7NVDiffRecMCCosine Distance0.04Unverified
#ModelMetricClaimedVerifiedStatus
1Metric3Dv2(L, FT)% < 11.2568.8Unverified
2PolyMaX(ConvNeXt-L)% < 11.2565.66Unverified
3iDisc% < 11.2563.8Unverified
4Bae et al.% < 11.2562.2Unverified
5Marigold + E2E FT(zero-shot)% < 11.2561.4Unverified
6Floors are Flat% < 11.2559.5Unverified
#ModelMetricClaimedVerifiedStatus
1Metric3Dv2 (g2, In-domain)% < 11.2577.8Unverified
2Bae et al.% < 11.2571.1Unverified
3Floors are Flat% < 11.2550.9Unverified
#ModelMetricClaimedVerifiedStatus
1Marigold + E2E FT(zero-shot)% < 11.2569.9Unverified
2Metric3Dv2(g2, ZS)% < 11.2569.7Unverified
#ModelMetricClaimedVerifiedStatus
1DSNRMSE12.2Unverified
#ModelMetricClaimedVerifiedStatus
1InvPTMean Angle Error14.15Unverified
#ModelMetricClaimedVerifiedStatus
1X-TC (Cross-Task Consistency)L1 error4.8Unverified