BA-Net: Dense Bundle Adjustment Network

06/13/2018
by   Chengzhou Tang, et al.
6

This paper introduces a neural network to solve the structure-from-motion (SfM) problem via feature bundle adjustment (BA), which explicitly enforces multi-view geometry constraints in the form of feature reprojection error. The whole pipeline is differentiable, so that the network can learn suitable feature representations that make the BA problem more trackable. Furthermore, this work introduces a novel depth parameterization to recover dense per-pixel depth. The network first generates some bases depth maps according to the input image, and optimizes the final depth as a linear combination of these bases via feature BA. The bases depth map generator is also learned via end-to-end training. The whole system nicely combines domain knowledge (i.e. hard-coded multi-view geometry constraints) and machine learning (i.e. feature learning and basis depth map generator learning) to address the challenging SfM problem. Experiments on large scale real data prove the success of the proposed method.

READ FULL TEXT

page 4

page 5

page 8

page 9

research
11/20/2020

RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty

We consider the problem of simultaneously estimating a dense depth map a...
research
08/04/2019

Adversarial View-Consistent Learning for Monocular Depth Estimation

This paper addresses the problem of Monocular Depth Estimation (MDE). Ex...
research
07/25/2022

nLMVS-Net: Deep Non-Lambertian Multi-View Stereo

We introduce a novel multi-view stereo (MVS) method that can simultaneou...
research
04/07/2018

MVSNet: Depth Inference for Unstructured Multi-view Stereo

We present an end-to-end deep learning architecture for depth map infere...
research
12/02/2020

Efficient Depth Completion Using Learned Bases

In this paper, we propose a new global geometry constraint for depth com...
research
09/07/2020

Improved Modeling of 3D Shapes with Multi-view Depth Maps

We present a simple yet effective general-purpose framework for modeling...
research
09/06/2018

Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis

Multi-omic data provides multiple views of the same patients. Integrativ...

Please sign up or login with your details

Forgot password? Click here to reset