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

arXiv: https://arxiv.org/abs/2304.12031 · HTML: https://mlsanity.com/paper/2304.12031/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 10 of 10)

- [DIODE: A Dense Indoor and Outdoor DEpth Dataset](https://mlsanity.com/paper/1908.00463/) (2019)
- [SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection](https://mlsanity.com/paper/2008.11351/) (2020)
- [Pothole Detection Based on Disparity Transformation and Road Surface Modeling](https://mlsanity.com/paper/1908.00894/) (2019)
- [GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation](https://mlsanity.com/paper/2012.06980/) (2020)
- [Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms](https://mlsanity.com/paper/2103.02433/) (2021)
- [SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection](https://mlsanity.com/paper/2107.14599/) (2021)
- [Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments](https://mlsanity.com/paper/2008.01963/) (2020)
- [Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots](https://mlsanity.com/paper/2008.11383/) (2020)
- [Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator](https://mlsanity.com/paper/2005.08165/) (2020)
- [SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming](https://mlsanity.com/paper/2208.08667/) (2022)

## Built on by (most cited first, 10 of 10)

- [Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think](https://mlsanity.com/paper/2409.11355/) (2024)
- [RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing](https://mlsanity.com/paper/2309.10356/) (2023)
- [RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion](https://mlsanity.com/paper/2407.21631/) (2024)
- [SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection](https://mlsanity.com/paper/2402.18918/) (2024)
- [SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning](https://mlsanity.com/paper/2407.05283/) (2024)
- [Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance](https://mlsanity.com/paper/2410.00386/) (2024)
- [Three-Filters-to-Normal+: Revisiting Discontinuity Discrimination in Depth-to-Normal Translation](https://mlsanity.com/paper/2312.07964/) (2023)
- [Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations](https://mlsanity.com/paper/2504.15121/) (2025)
- [An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2603.27238/) (2026)
- [OT-Drive: Out-of-Distribution Off-Road Traversable Area Segmentation via Optimal Transport](https://mlsanity.com/paper/2601.09952/) (2026)

## Abstract (arXiv)

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.