Browse State-of-the-Art › Surface Normal Estimation
Surface Normal Estimation
46 papers with code · 0 benchmarks · 5 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
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
5 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: 96 · with a code link: 46 · where Syntology ran a sample: 18 (14 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 96 tagged: 14 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 96 of 96, 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.
-
18 Nov 2014 4 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling.
-
13 Mar 2018 3 repositories listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 3 pointer-only (licence)Maintaining natural image statistics is a crucial factor in restoration and generation of realistic looking images.
-
22 Aug 2024 2 repositories listed Syntology 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction.
-
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.
-
20 Feb 2023 2 repositories listedWe present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
-
17 Jun 2022 2 repositories listedMulti-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes.
-
13 Dec 2020 2 repositories listedNote that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve the quality of 3D reconstruction and pixel-wise accuracy of depth and surface normals.
-
3 May 2019 2 repositories listedSelf-supervised learning aims to learn representations from the data itself without explicit manual supervision.
-
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.
-
11 Mar 2025 1 repository listedWhile surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored.
-
4 Nov 2024 1 repository listedOur first innovation is our MTL architecture, which enhances predictions for both tasks by integrating geometric information from depth and surface normal estimation, enabling a deeper understanding of 3D scene…
-
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.
-
22 Mar 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training.
-
10 Mar 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 2 pointer-only (licence)Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks.
-
1 Mar 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks.
-
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…
-
6 Nov 2023 1 repository listedHolistic scene understanding includes semantic segmentation, surface normal estimation, object boundary detection, depth estimation, etc.
-
31 Oct 2023 1 repository listedIn addition, the encoding is decodable, which enables neural networks to regress continuous objects by regressing their encodings.
-
27 Oct 2023 1 repository listedOur FOUND approach tackles this, with 4 main contributions: (i) SynFoot, a synthetic dataset of 50, 000 photorealistic foot images, paired with ground truth surface normals and keypoints; (ii) an uncertainty-aware…
-
28 Jul 2023 1 repository listedTask-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods.
-
30 May 2023 1 repository listedIn this work, we propose using a condition number of a linear system of gradients as a stability criterion of an MTL optimization.
-
24 Apr 2023 1 repository listedSurface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information.
-
21 Oct 2022 1 repository listedFine-detailed reconstructions are in high demand in many applications.
-
13 Oct 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) · 1 unverified (of 3 harvested samples)In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks, a quality of meta learning.
-
20 Jul 2022 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)Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption.
-
14 Jul 2022 1 repository listedWe present a multimodal spatial rectifier that stabilizes the egocentric images to a set of reference directions, which allows learning a coherent visual representation.
-
17 May 2022 1 repository listed Syntology 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) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)At the heart of our approach is a shared attention mechanism modeling the dependencies across the tasks.
-
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.
-
2 Mar 2022 1 repository listed
-
11 Oct 2021 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: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
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)
-
15 Aug 2021 1 repository listed
-
22 Mar 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result (of 11 harvested samples)
-
7 Aug 2020 1 repository listed
-
17 Jul 2020 1 repository listed
-
7 Jun 2020 1 repository listed
-
20 Dec 2019 1 repository listed
-
6 Apr 2019 1 repository listed
-
29 Mar 2019 1 repository listed
-
1 Dec 2018 1 repository listed
-
1 Jun 2018 1 repository listed
-
3 May 2018 1 repository listed
-
23 Oct 2017 1 repository listed
-
21 Feb 2017 1 repository listed
-
Probabilistic Online Event Downsampling3 Jun 2025 0 repositories listed
-
Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations21 Apr 2025 0 repositories listed
-
NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors15 Apr 2025 0 repositories listed
-
Image Gradient-Aided Photometric Stereo Network16 Dec 2024 0 repositories listed
-
Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration18 Aug 2024 0 repositories listed
-
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal24 Jun 2024 0 repositories listed
-
Enabling Visual Recognition at Radio Frequency29 May 2024 0 repositories listed
-
PanoNormal: Monocular Indoor 360° Surface Normal Estimation29 May 2024 0 repositories listed
-
Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning15 Mar 2024 0 repositories listed
-
Surface Normal Estimation with Transformers11 Jan 2024 0 repositories listed
-
Event-based Shape from Polarization with Spiking Neural Networks26 Dec 2023 0 repositories listed
-
RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation21 Nov 2023 0 repositories listed
-
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement21 Oct 2023 0 repositories listed
-
18 Sep 2023 0 repositories listed
-
TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation23 Jul 2023 0 repositories listed
-
Pointersect: Neural Rendering with Cloud-Ray Intersection24 Apr 2023 0 repositories listed
-
Event Fusion Photometric Stereo Network1 Mar 2023 0 repositories listed
-
A Large-Scale Homography Benchmark1 Jan 2023 0 repositories listed
-
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision1 Jan 2023 0 repositories listed
-
DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond1 Jan 2023 0 repositories listed
-
Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence1 Jan 2023 0 repositories listed
-
Multi-Task Learning with Knowledge Distillation for Dense Prediction1 Jan 2023 0 repositories listed
-
ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo1 Jan 2023 0 repositories listed
-
Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps17 Sep 2022 0 repositories listed
-
TransNet: Category-Level Transparent Object Pose Estimation22 Aug 2022 0 repositories listed
-
SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming18 Aug 2022 0 repositories listed
-
17 Jun 2022 0 repositories listed
-
Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields9 Jun 2022 0 repositories listed
-
Multi-Task Self-Training for Learning General Representations25 Aug 2021 0 repositories listed
-
SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection30 Jul 2021 0 repositories listed
-
Single Image Depth Estimation: An Overview13 Apr 2021 0 repositories listed
-
Streaming Self-Training via Domain-Agnostic Unlabeled Images7 Apr 2021 0 repositories listed
-
Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention1 Aug 2020 0 repositories listed
-
SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data1 Aug 2020 0 repositories listed
-
What is Learned in Deep Uncalibrated Photometric Stereo?1 Aug 2020 0 repositories listed
-
SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data30 Jul 2020 0 repositories listed
-
Improving task-specific representation via 1M unlabelled images without any extra knowledge24 Jun 2020 0 repositories listed
-
Attentive Feature Reuse for Multi Task Meta learning12 Jun 2020 0 repositories listed
-
VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines1 Jun 2020 0 repositories listed
-
VisualEchoes: Spatial Image Representation Learning through Echolocation4 May 2020 0 repositories listed
-
Task-Assisted Domain Adaptation with Anchor Tasks16 Aug 2019 0 repositories listed
-
Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network1 Jul 2019 0 repositories listed
-
1 Mar 2019 0 repositories listed
-
Transitive Invariance for Self-supervised Visual Representation Learning9 Aug 2017 0 repositories listed
-
Pano2CAD: Room Layout From A Single Panorama Image29 Sep 2016 0 repositories listed
-
PixelNet: Towards a General Pixel-level Architecture21 Sep 2016 0 repositories listed
-
Fine-scale Surface Normal Estimation using a Single NIR Image24 Mar 2016 0 repositories listed
-
Depth and Surface Normal Estimation From Monocular Images Using Regression on Deep Features and Hierarchical CRFs1 Jun 2015 0 repositories listed
-
Unsupervised Learning of Visual Representations using Videos4 May 2015 0 repositories listed
-
Designing Deep Networks for Surface Normal Estimation18 Nov 2014 0 repositories listed
Syntology lines on 18 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