PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation

TL;DR

PatchRefiner is a novel framework that improves high-resolution monocular depth estimation in real-world scenarios by leveraging synthetic data and a tile-based refinement approach, achieving significant performance gains.

Contribution

It introduces a tile-based refinement framework with a pseudo-labeling strategy and DSD loss for effective synthetic-to-real transfer in high-resolution depth estimation.

Findings

Outperforms benchmarks on Unreal4KStereo with 18.1% RMSE reduction

Enhances detail accuracy and scale consistency on real datasets

Demonstrates superior performance in high-resolution depth estimation

Abstract

This paper introduces PatchRefiner, an advanced framework for metric single image depth estimation aimed at high-resolution real-domain inputs. While depth estimation is crucial for applications such as autonomous driving, 3D generative modeling, and 3D reconstruction, achieving accurate high-resolution depth in real-world scenarios is challenging due to the constraints of existing architectures and the scarcity of detailed real-world depth data. PatchRefiner adopts a tile-based methodology, reconceptualizing high-resolution depth estimation as a refinement process, which results in notable performance enhancements. Utilizing a pseudo-labeling strategy that leverages synthetic data, PatchRefiner incorporates a Detail and Scale Disentangling (DSD) loss to enhance detail capture while maintaining scale accuracy, thus facilitating the effective transfer of knowledge from synthetic to real-world data. Our extensive evaluations demonstrate PatchRefiner's superior performance, significantly outperforming existing benchmarks on the Unreal4KStereo dataset by 18.1% in terms of the root mean squared error (RMSE) and showing marked improvements in detail accuracy and consistent scale estimation on diverse real-world datasets like CityScape, ScanNet++, and ETH3D.