Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video

05/07/2020
by   Peng Wang, et al.
0

Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction methods because thin structures often lack distinct point features and have severe self-occlusion. We propose the first approach that simultaneously estimates camera motion and reconstructs the geometry of complex 3D thin structures in high quality from a color video captured by a handheld camera. Specifically, we present a new curve-based approach to estimate accurate camera poses by establishing correspondences between featureless thin objects in the foreground in consecutive video frames, without requiring visual texture in the background scene to lock on. Enabled by this effective curve-based camera pose estimation strategy, we develop an iterative optimization method with tailored measures on geometry, topology as well as self-occlusion handling for reconstructing 3D thin structures. Extensive validations on a variety of thin structures show that our method achieves accurate camera pose estimation and faithful reconstruction of 3D thin structures with complex shape and topology at a level that has not been attained by other existing reconstruction methods.

READ FULL TEXT
research
05/07/2020

Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video

Thin structures, such as wire-frame sculptures, fences, cables, power li...
research
01/25/2017

Recovering 3D Planar Arrangements from Videos

Acquiring 3D geometry of real world objects has various applications in ...
research
04/05/2022

Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows

Existing approaches for Structure from Motion (SfM) produce impressive 3...
research
02/11/2016

A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation

Generative reconstruction methods compute the 3D configuration (such as ...
research
07/12/2021

CurveFusion: Reconstructing Thin Structures from RGBD Sequences

We introduce CurveFusion, the first approach for high quality scanning o...
research
12/14/2020

Continuous Curve Textures

Repetitive patterns are ubiquitous in natural and human-made objects, an...
research
01/24/2022

Consistent 3D Hand Reconstruction in Video via self-supervised Learning

We present a method for reconstructing accurate and consistent 3D hands ...

Please sign up or login with your details

Forgot password? Click here to reset