Browse State-of-the-Art › Surface Normals Estimation
Surface Normals Estimation
33 papers with code · 8 benchmarks · 12 datasets archive 2025-07-28
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.
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 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): NYU Depth v2 (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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.
Papers archive 2025-07-28
archive papers tagged: 39 · with a code link: 33 · where Syntology ran a sample: 17 (11 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (17 of 39 tagged: 11 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 39 of 39, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
25 Oct 2019 4 repositories listedBlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.
-
13 Sep 2018 4 repositories listed Syntology official (archive's flag): 3 ran · 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 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.
-
13 Apr 2023 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 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.
-
24 Nov 2021 2 repositories listedWe present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
-
16 Sep 2019 2 repositories listedWe 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.
-
15 Apr 2019 2 repositories listedThis 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…
-
10 Apr 2019 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 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.
-
17 Sep 2024 1 repository listed Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 17 harvested samples) · 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.
-
9 Nov 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)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…
-
24 Oct 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.
-
4 Aug 2023 1 repository listedMSECNet consists of a backbone network and a multi-scale edge conditioning (MSEC) stream.
-
27 Jun 2023 1 repository listedWe 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…
-
29 Mar 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (of 11 harvested samples)Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images.
-
30 Nov 2022 1 repository listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 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).
-
13 Oct 2022 1 repository listedTo 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…
-
23 Jul 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds.
-
7 Jun 2022 1 repository listedUnfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging.
-
28 Apr 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Computer vision models excel at making predictions when the test distribution closely resembles the training distribution.
-
15 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 1 pointer-only (licence)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.
-
20 Sep 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)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.
-
12 Aug 2021 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified (of 17 harvested samples) · 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.
-
3 Jun 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties.
-
7 Dec 2020 1 repository listedThis problem is inherently more challenging when the illumination is not a single light source under laboratory conditions but is instead an unconstrained environmental illumination.
-
26 Nov 2020 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)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.
-
13 Jul 2020 1 repository listedWith AIP, it is trivial to capture the same image under different conditions (e. g., fidelity, lighting, etc.)
-
7 Jun 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Visual perception entails solving a wide set of tasks, e. g., object detection, depth estimation, etc.
-
7 Jun 2020 1 repository listedIdeally, this results in images from two domains that present shared information to the primary network.
-
1 Jun 2020 1 repository listedVisual perception entails solving a wide set of tasks (e. g., object detection, depth estimation, etc).
-
23 Mar 2020 1 repository listedWe propose a surface fitting method for unstructured 3D point clouds.
-
6 Oct 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 8 harvested samples) · 1 pointer-only (licence)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.
-
16 Jun 2019 1 repository listed
-
1 Jun 2019 1 repository listed
-
3 Dec 2018 1 repository listed
-
Learning from the Giants: A Practical Approach to Underwater Depth and Surface Normals Estimation2 Oct 2024 0 repositories listed
-
18 Sep 2023 0 repositories listed
-
26 Apr 2023 0 repositories listed
-
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision1 Jan 2023 0 repositories listed
-
1 Apr 2021 0 repositories listed
-
13 Oct 2020 0 repositories listed
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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections