D2NT: A High-Performing Depth-to-Normal Translator

TL;DR

This paper introduces D2NT, a fast and accurate depth-to-normal translation method that improves surface normal estimation by combining a novel translator, a discontinuity-aware gradient filter, and a refinement module, achieving state-of-the-art results.

Contribution

The paper presents a novel depth-to-normal translator, a discontinuity-aware gradient filter, and a refinement module, advancing real-time surface normal estimation with improved accuracy and efficiency.

Findings

Achieves state-of-the-art accuracy among real-time surface normal estimators.

Demonstrates the best efficiency-accuracy trade-off in the field.

Provides a versatile refinement module compatible with existing methods.

Abstract

Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this dilemma, this paper first presents a superfast depth-to-normal translator (D2NT), which can directly translate depth images into surface normal maps without calculating 3D coordinates. We then propose a discontinuity-aware gradient (DAG) filter, which adaptively generates gradient convolution kernels to improve depth gradient estimation. Finally, we propose a surface normal refinement module that can easily be integrated into any depth-to-normal SNEs, substantially improving the surface normal estimation accuracy. Our proposed algorithm demonstrates the best accuracy among all other existing real-time SNEs and achieves the SoTA trade-off between efficiency and accuracy.