Robust Depth Estimation from Auto Bracketed Images

TL;DR

This paper introduces a robust depth estimation method from short burst images with varied exposure or noise, improving accuracy in low-light conditions for smartphones and cameras.

Contribution

We propose a novel geometric transformation between flow and depth and integrate it into a residual-flow network for effective depth estimation from bracketed images.

Findings

Outperforms state-of-the-art methods on multiple datasets

Produces accurate depth maps in low-light and noisy conditions

Enables applications in image enhancement and editing

Abstract

As demand for advanced photographic applications on hand-held devices grows, these electronics require the capture of high quality depth. However, under low-light conditions, most devices still suffer from low imaging quality and inaccurate depth acquisition. To address the problem, we present a robust depth estimation method from a short burst shot with varied intensity (i.e., Auto Bracketing) or strong noise (i.e., High ISO). We introduce a geometric transformation between flow and depth tailored for burst images, enabling our learning-based multi-view stereo matching to be performed effectively. We then describe our depth estimation pipeline that incorporates the geometric transformation into our residual-flow network. It allows our framework to produce an accurate depth map even with a bracketed image sequence. We demonstrate that our method outperforms state-of-the-art methods for various datasets captured by a smartphone and a DSLR camera. Moreover, we show that the estimated depth is applicable for image quality enhancement and photographic editing.