Dense Depth from Event Focal Stack

TL;DR

This paper introduces a neural network-based approach for dense depth estimation from event streams generated by a focal stack, trained on synthetic data to handle diverse 3D scenes and real-world domain gaps.

Contribution

It presents a novel method using synthesized event focal stacks for training, enabling accurate depth estimation from event cameras in various scenes.

Findings

Outperforms depth-from-defocus methods on synthetic and real datasets

Effective training on synthetic data reduces domain gap issues

Demonstrates superior depth estimation accuracy

Abstract

We propose a method for dense depth estimation from an event stream generated when sweeping the focal plane of the driving lens attached to an event camera. In this method, a depth map is inferred from an ``event focal stack'' composed of the event stream using a convolutional neural network trained with synthesized event focal stacks. The synthesized event stream is created from a focal stack generated by Blender for any arbitrary 3D scene. This allows for training on scenes with diverse structures. Additionally, we explored methods to eliminate the domain gap between real event streams and synthetic event streams. Our method demonstrates superior performance over a depth-from-defocus method in the image domain on synthetic and real datasets.