Surface Normals Estimation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

12 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 33 papers with code (39 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• BlenderProc
  25 Oct 2019 4 repositories listed
  BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.
• Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
  13 Sep 2018 4 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 6 pointer-only (licence)
  Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
• iDisc: Internal Discretization for Monocular Depth Estimation
  13 Apr 2023 2 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  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.
• Extracting Triangular 3D Models, Materials, and Lighting From Images
  24 Nov 2021 2 repositories listed
  We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
• 360ᵒ Surface Regression with a Hyper-Sphere Loss
  16 Sep 2019 2 repositories listed
  We present a dataset of 360ᵒ 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.
• Deep Iterative Surface Normal Estimation
  15 Apr 2019 2 repositories listed
  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…
• Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
  10 Apr 2019 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  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.
• Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
  17 Sep 2024 1 repository listed Syntology ran 16 of 17 samples · 1 unverified · 17 pointer-only (licence)
  Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task.
• PolyMaX: General Dense Prediction with Mask Transformer
  9 Nov 2023 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  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…
• Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
  24 Oct 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.
• MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning
  4 Aug 2023 1 repository listed
  MSECNet consists of a backbone network and a multi-scale edge conditioning (MSEC) stream.
• MIMIC: Masked Image Modeling with Image Correspondences
  27 Jun 2023 1 repository listed
  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…
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
  29 Mar 2023 1 repository listed Syntology ran 1 of 11 samples · 10 unverified
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images.
• NeAF: Learning Neural Angle Fields for Point Normal Estimation
  30 Nov 2022 1 repository listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  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).
• HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
  13 Oct 2022 1 repository listed
  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…
• GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation
  23 Jul 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds.
• Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
  7 Jun 2022 1 repository listed
  Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging.
• GRIT: General Robust Image Task Benchmark
  28 Apr 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Computer vision models excel at making predictions when the test distribution closely resembles the training distribution.
• InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
  15 Mar 2022 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  Multi-task dense scene understanding is a thriving research domain that requires simultaneous perception and reasoning on a series of correlated tasks with pixel-wise prediction.
• Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation
  20 Sep 2021 1 repository listed Syntology ran 6 of 6 samples · 0 unverified
  Experimental results show that the proposed method outperforms the state-of-the-art in ScanNet and NYUv2, and that the estimated uncertainty correlates well with the prediction error.
• AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds
  12 Aug 2021 1 repository listed Syntology ran 9 of 17 samples · 8 unverified · 17 pointer-only (licence)
  Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points.
• NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
  3 Jun 2021 1 repository listed Syntology ran 0 of 5 samples · 5 unverified
  This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties.
• NeRD: Neural Reflectance Decomposition from Image Collections
  7 Dec 2020 1 repository listed
  This problem is inherently more challenging when the illumination is not a single light source under laboratory conditions but is instead an unconstrained environmental illumination.
• How Well Do Self-Supervised Models Transfer?
  26 Nov 2020 1 repository listed Syntology ran 4 of 5 samples · 1 unverified
  We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction.
• AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning
  13 Jul 2020 1 repository listed
  With AIP, it is trivial to capture the same image under different conditions (e.
• Robust Learning Through Cross-Task Consistency
  7 Jun 2020 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Visual perception entails solving a wide set of tasks, e.
• SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
  7 Jun 2020 1 repository listed
  Ideally, this results in images from two domains that present shared information to the primary network.
• Robust Learning Through Cross-Task Consistency
  1 Jun 2020 1 repository listed
  Visual perception entails solving a wide set of tasks (e.
• DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
  23 Mar 2020 1 repository listed
  We propose a surface fitting method for unstructured 3D point clouds.
• ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
  6 Oct 2019 1 repository listed Syntology ran 0 of 8 samples · 8 unverified
  To address these challenges, we present ClearGrasp -- a deep learning approach for estimating accurate 3D geometry of transparent objects from a single RGB-D image for robotic manipulation.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.