HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization

by   Zhihao Liang, et al.

Recovery of an underlying scene geometry from multiview images stands as a long-time challenge in computer vision research. The recent promise leverages neural implicit surface learning and differentiable volume rendering, and achieves both the recovery of scene geometry and synthesis of novel views, where deep priors of neural models are used as an inductive smoothness bias. While promising for object-level surfaces, these methods suffer when coping with complex scene surfaces. In the meanwhile, traditional multi-view stereo can recover the geometry of scenes with rich textures, by globally optimizing the local, pixel-wise correspondences across multiple views. We are thus motivated to make use of the complementary benefits from the two strategies, and propose a method termed Helix-shaped neural implicit Surface learning or HelixSurf; HelixSurf uses the intermediate prediction from one strategy as the guidance to regularize the learning of the other one, and conducts such intertwined regularization iteratively during the learning process. We also propose an efficient scheme for differentiable volume rendering in HelixSurf. Experiments on surface reconstruction of indoor scenes show that our method compares favorably with existing methods and is orders of magnitude faster, even when some of existing methods are assisted with auxiliary training data. The source code is available at https://github.com/Gorilla-Lab-SCUT/HelixSurf.


page 7

page 12

page 13

page 15

page 16

page 17

page 18

page 19


Dynamic Multi-View Scene Reconstruction Using Neural Implicit Surface

Reconstructing general dynamic scenes is important for many computer vis...

NeRF, meet differential geometry!

Neural radiance fields, or NeRF, represent a breakthrough in the field o...

Enhancing Neural Rendering Methods with Image Augmentations

Faithfully reconstructing 3D geometry and generating novel views of scen...

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

In this work, we present a new multi-view depth estimation method that u...

Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations

Neural Radiance Field (NeRF) regresses a neural parameterized scene by d...

Level-S^2fM: Structure from Motion on Neural Level Set of Implicit Surfaces

This paper presents a neural incremental Structure-from-Motion (SfM) app...

GA-Sketching: Shape Modeling from Multi-View Sketching with Geometry-Aligned Deep Implicit Functions

Sketch-based shape modeling aims to bridge the gap between 2D drawing an...

Please sign up or login with your details

Forgot password? Click here to reset