Surface Normal Estimation with Transformers
- URL: http://arxiv.org/abs/2401.05745v1
- Date: Thu, 11 Jan 2024 08:52:13 GMT
- Title: Surface Normal Estimation with Transformers
- Authors: Barry Shichen Hu, Siyun Liang, Johannes Paetzold, Huy H. Nguyen, Isao
Echizen, Jiapeng Tang
- Abstract summary: We propose a Transformer to accurately predict normals from point clouds with noise and density variations.
Our method achieves state-of-the-art performance on both the synthetic shape dataset PCPNet, and the real-world indoor scene PCPNN.
- Score: 11.198936434401382
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose the use of a Transformer to accurately predict normals from point
clouds with noise and density variations. Previous learning-based methods
utilize PointNet variants to explicitly extract multi-scale features at
different input scales, then focus on a surface fitting method by which local
point cloud neighborhoods are fitted to a geometric surface approximated by
either a polynomial function or a multi-layer perceptron (MLP). However,
fitting surfaces to fixed-order polynomial functions can suffer from
overfitting or underfitting, and learning MLP-represented hyper-surfaces
requires pre-generated per-point weights. To avoid these limitations, we first
unify the design choices in previous works and then propose a simplified
Transformer-based model to extract richer and more robust geometric features
for the surface normal estimation task. Through extensive experiments, we
demonstrate that our Transformer-based method achieves state-of-the-art
performance on both the synthetic shape dataset PCPNet, and the real-world
indoor scene dataset SceneNN, exhibiting more noise-resilient behavior and
significantly faster inference. Most importantly, we demonstrate that the
sophisticated hand-designed modules in existing works are not necessary to
excel at the task of surface normal estimation.
Related papers
- ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics.
We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal.
Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
arXiv Detail & Related papers (2024-08-22T17:59:01Z) - Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization.
Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information.
Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
arXiv Detail & Related papers (2024-05-23T14:39:52Z) - NeuralGF: Unsupervised Point Normal Estimation by Learning Neural
Gradient Function [55.86697795177619]
Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing.
We introduce a new paradigm for learning neural gradient functions, which encourages the neural network to fit the input point clouds.
Our excellent results on widely used benchmarks demonstrate that our method can learn more accurate normals for both unoriented and oriented normal estimation tasks.
arXiv Detail & Related papers (2023-11-01T09:25:29Z) - Explicit Neural Surfaces: Learning Continuous Geometry With Deformation
Fields [33.38609930708073]
We introduce Explicit Neural Surfaces (ENS), an efficient smooth surface representation that encodes topology with a deformation field from a known base domain.
Compared to implicit surfaces, ENS trains faster and has several orders of magnitude faster inference times.
arXiv Detail & Related papers (2023-06-05T15:24:33Z) - Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud
Normal Estimation [39.79759035338819]
We present two basic design principles to bridge the gap between estimated and precise surface normals.
We implement these two principles using deep neural networks, and integrate them with the state-of-the-art (SOTA) normal estimation methods in a plug-and-play manner.
arXiv Detail & Related papers (2023-03-30T05:59:43Z) - HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper
Surfaces [54.77683371400133]
We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations.
Experimental results show that our HSurf-Net achieves the state-of-the-art performance on the synthetic shape dataset.
arXiv Detail & Related papers (2022-10-13T16:39:53Z) - PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result.
Recent transformer-based image recognition model andTT show consistent efficiency gain.
arXiv Detail & Related papers (2021-09-15T01:10:30Z) - AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds [31.641383879577894]
This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations.
Existing works use a network to learn point-wise weights for weighted least surface fitting to estimate the normals.
We propose a simple yet effective solution that adds an additional offset prediction to improve the quality of normal estimation.
arXiv Detail & Related papers (2021-08-12T16:37:24Z) - PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows [58.96306192736593]
We present PU-Flow, which incorporates normalizing flows and feature techniques to produce dense points uniformly distributed on the underlying surface.
Specifically, we formulate the upsampling process as point in a latent space, where the weights are adaptively learned from local geometric context.
We show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.
arXiv Detail & Related papers (2021-07-13T07:45:48Z) - DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares [43.24287146191367]
We propose a surface fitting method for unstructured 3D point clouds.
This method, called DeepFit, incorporates a neural network to learn point-wise weights for weighted least squares surface fitting.
arXiv Detail & Related papers (2020-03-23T09:18:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.