# Discontinuous and Smooth Depth Completion with Binary Anisotropic Diffusion Tensor

arXiv: https://arxiv.org/abs/2006.14374 · HTML: https://mlsanity.com/paper/2006.14374/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [A Surface Geometry Model for LiDAR Depth Completion](https://mlsanity.com/paper/2104.08466/) (2021)
- [DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network](https://mlsanity.com/paper/2108.12655/) (2021)
- [Deterministic Guided LiDAR Depth Map Completion](https://mlsanity.com/paper/2106.07256/) (2021)
- [Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching](https://mlsanity.com/paper/2210.01436/) (2022)
- [A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks](https://mlsanity.com/paper/2504.05150/) (2025)

## Abstract (arXiv)

We propose an unsupervised real-time dense depth completion from a sparse depth map guided by a single image. Our method generates a smooth depth map while preserving discontinuity between different objects. Our key idea is a Binary Anisotropic Diffusion Tensor (B-ADT) which can completely eliminate smoothness constraint at intended positions and directions by applying it to variational regularization. We also propose an Image-guided Nearest Neighbor Search (IGNNS) to derive a piecewise constant depth map which is used for B-ADT derivation and in the data term of the variational energy. Our experiments show that our method can outperform previous unsupervised and semi-supervised depth completion methods in terms of accuracy. Moreover, since our resulting depth map preserves the discontinuity between objects, the result can be converted to a visually plausible point cloud. This is remarkable since previous methods generate unnatural surface-like artifacts between discontinuous objects.