Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction

04/12/2023
by   Xiangyu Xu, et al.
3

Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules. However, this approach is constrained by higher memory expenses and limited representation capabilities. In this paper, we introduce a novel dynamic grid optimization method for high-fidelity 3D surface reconstruction that incorporates both RGB and depth observations. Rather than treating each voxel equally, we optimize the process by dynamically modifying the grid and assigning more finer-scale voxels to regions with higher complexity, allowing us to capture more intricate details. Furthermore, we develop a scheme to quantify the dynamic subdivision of voxel grid during optimization without requiring any priors. The proposed approach is able to generate high-quality 3D reconstructions with fine details on both synthetic and real-world data, while maintaining computational efficiency, which is substantially faster than the baseline method NeuralRGBD.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

page 9

page 10

page 11

research
06/29/2022

GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction

We present GO-Surf, a direct feature grid optimization method for accura...
research
08/26/2022

Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

Neural surface reconstruction aims to reconstruct accurate 3D surfaces b...
research
06/10/2022

Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

In this technical report, we improve the DVGO framework (called DVGOv2),...
research
06/05/2023

Neuralangelo: High-Fidelity Neural Surface Reconstruction

Neural surface reconstruction has been shown to be powerful for recoveri...
research
04/26/2023

VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs

Neural Radiance Fields (NeRF) has shown great success in novel view synt...
research
02/03/2022

HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits

Reconstruction of high-fidelity 3D objects or scenes is a fundamental re...
research
04/04/2023

FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction

Recent works on 3D reconstruction from posed images have demonstrated th...

Please sign up or login with your details

Forgot password? Click here to reset