Improved surface reconstruction using high-frequency details

• URL: http://arxiv.org/abs/2206.07850v1
• Date: Wed, 15 Jun 2022 23:46:48 GMT
• Title: Improved surface reconstruction using high-frequency details
• Authors: Yiqun Wang, Ivan Skorokhodov, Peter Wonka
• Abstract summary: We propose a novel method to improve the quality of surface reconstruction in neural rendering. Our results show that our method can reconstruct high-frequency surface details and obtain better surface reconstruction quality than the current state of the art.
• Score: 44.73668037810989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural rendering can be used to reconstruct implicit representations of shapes without 3D supervision. However, current neural surface reconstruction methods have difficulty learning high-frequency details of shapes, so that the reconstructed shapes are often oversmoothed. We propose a novel method to improve the quality of surface reconstruction in neural rendering. We follow recent work to model surfaces as signed distance fields. First, we offer a derivation to analyze the relationship between the signed distance function, the volume density, the transparency function, and the weighting function used in the volume rendering equation. Second, we observe that attempting to jointly encode high-frequency and low frequency components in a single signed distance function leads to unstable optimization. We propose to decompose the signed distance function in a base function and a displacement function together with a coarse-to-fine strategy to gradually increase the high-frequency details. Finally, we propose to use an adaptive strategy that enables the optimization to focus on improving certain regions near the surface where the signed distance fields have artifacts. Our qualitative and quantitative results show that our method can reconstruct high-frequency surface details and obtain better surface reconstruction quality than the current state of the art. Code will be released at https://github.com/yiqun-wang/HFS.

Related papers

• VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations [25.88881764546414]
  VQ-NeRF is an efficient pipeline for enhancing implicit neural representations via vector quantization. We present an innovative multi-scale NeRF sampling scheme that concurrently optimize the NeRF model at both compressed and original scales. We incorporate a semantic loss function to improve the geometric fidelity and semantic coherence of our 3D reconstructions.
  arXiv  Detail & Related papers  (2023-10-23T01:41:38Z)
• Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail [54.03399077258403]
  We present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Our representation aggregates space features from a multi-convolved featurization within a conical frustum along a ray.
  arXiv  Detail & Related papers  (2023-09-19T05:44:00Z)
• Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds [53.02191521770926]
  We introduce Neural Poisson Surface Reconstruction (nPSR), an architecture for shape reconstruction that addresses the challenge of recovering 3D shapes from points. nPSR exhibits two main advantages: First, it enables efficient training on low-resolution data while achieving comparable performance at high-resolution evaluation. Overall, the neural Poisson surface reconstruction not only improves upon the limitations of classical deep neural networks in shape reconstruction but also achieves superior results in terms of reconstruction quality, running time, and resolution agnosticism.
  arXiv  Detail & Related papers  (2023-08-03T13:56:07Z)
• NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies [87.06532943371575]
  We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation.
  arXiv  Detail & Related papers  (2022-11-25T15:21:45Z)
• Recovering Fine Details for Neural Implicit Surface Reconstruction [3.9702081347126943]
  We present D-NeuS, a volume rendering neural implicit surface reconstruction method capable to recover fine geometry details. We impose multi-view feature consistency on the surface points, derived by interpolating SDF zero-crossings from sampled points along rays. Our method reconstructs high-accuracy surfaces with details, and outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-11-21T10:06:09Z)
• Sphere-Guided Training of Neural Implicit Surfaces [14.882607960908217]
  In 3D reconstruction, neural distance functions trained via ray marching have been widely adopted for multi-view 3D reconstruction. These methods, however, apply the ray marching procedure for the entire scene volume, leading to reduced sampling efficiency. We address this problem via joint training of the implicit function and our new coarse sphere-based surface reconstruction.
  arXiv  Detail & Related papers  (2022-09-30T15:00:03Z)
• Volume Rendering of Neural Implicit Surfaces [57.802056954935495]
  This paper aims to improve geometry representation and reconstruction in neural volume rendering. We achieve that by modeling the volume density as a function of the geometry. Applying this new density representation to challenging scene multiview datasets produced high quality geometry reconstructions.
  arXiv  Detail & Related papers  (2021-06-22T20:23:16Z)
• NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction [88.02850205432763]
  We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision. We observe that the conventional volume rendering method causes inherent geometric errors for surface reconstruction. We propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision.
  arXiv  Detail & Related papers  (2021-06-20T12:59:42Z)
• Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations [21.64457003420851]
  We develop a hybrid neural surface representation that allows us to impose geometry-aware sampling and regularization. We demonstrate that our method can be adopted to improve techniques for reconstructing neural implicit surfaces from multi-view images or point clouds.
  arXiv  Detail & Related papers  (2020-12-11T15:51:04Z)

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.