Robust Depth Estimation from Auto Bracketed Images
This addresses the need for high-quality depth in photographic applications on handheld devices, though it appears incremental as it builds on existing multi-view stereo matching with tailored geometric transformations.
The paper tackles the problem of inaccurate depth estimation from handheld devices under low-light conditions by proposing a robust method using auto-bracketed images, demonstrating that it outperforms state-of-the-art methods on datasets from smartphones and DSLR cameras.
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.