# Indoor Depth Completion with Boundary Consistency and Self-Attention

arXiv: https://arxiv.org/abs/1908.08344 · HTML: https://mlsanity.com/paper/1908.08344/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2019.

## Built on by (most cited first, 29 of 29)

- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation](https://mlsanity.com/paper/2406.12849/) (2024)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [Beyond Image to Depth: Improving Depth Prediction using Echoes](https://mlsanity.com/paper/2103.08468/) (2021)
- [Point Scene Understanding via Disentangled Instance Mesh Reconstruction](https://mlsanity.com/paper/2203.16832/) (2022)
- [RGB-Depth Fusion GAN for Indoor Depth Completion](https://mlsanity.com/paper/2203.10856/) (2022)
- [Robust Depth Completion with Uncertainty-Driven Loss Functions](https://mlsanity.com/paper/2112.07895/) (2021)
- [Mirror3D: Depth Refinement for Mirror Surfaces](https://mlsanity.com/paper/2106.06629/) (2021)
- [FDCT: Fast Depth Completion for Transparent Objects](https://mlsanity.com/paper/2307.12274/) (2023)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2309.00655/) (2023)
- [S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation](https://mlsanity.com/paper/2103.02396/) (2021)
- [Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM](https://mlsanity.com/paper/2204.13877/) (2022)
- [AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completion](https://mlsanity.com/paper/2309.01624/) (2023)
- [RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion](https://mlsanity.com/paper/2306.03584/) (2023)
- [Towards Domain-agnostic Depth Completion](https://mlsanity.com/paper/2207.14466/) (2022)
- [DeepDR: Deep Structure-Aware RGB-D Inpainting for Diminished Reality](https://mlsanity.com/paper/2312.00532/) (2023)
- [HI-GAN: Hierarchical Inpainting GAN with Auxiliary Inputs for Combined RGB and Depth Inpainting](https://mlsanity.com/paper/2402.10334/) (2024)
- [Self-Guided Instance-Aware Network for Depth Completion and Enhancement](https://mlsanity.com/paper/2105.12186/) (2021)
- [A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion](https://mlsanity.com/paper/2406.09792/) (2024)
- [Deep Cost Ray Fusion for Sparse Depth Video Completion](https://mlsanity.com/paper/2409.14935/) (2024)
- [Indoor Semantic Scene Understanding using Multi-modality Fusion](https://mlsanity.com/paper/2108.07616/) (2021)
- [V-LinkNet: Learning Contextual Inpainting Across Latent Space of Generative Adversarial Network](https://mlsanity.com/paper/2201.00323/) (2022)
- [Object Semantics Give Us the Depth We Need: Multi-task Approach to Aerial Depth Completion](https://mlsanity.com/paper/2304.12542/) (2023)
- [MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion](https://mlsanity.com/paper/2412.13848/) (2024)
- [MT-Depth: Multi-task Instance feature analysis for the Depth Completion](https://mlsanity.com/paper/2512.04734/) (2025)

## Abstract (arXiv)

Depth estimation features are helpful for 3D recognition. Commodity-grade depth cameras are able to capture depth and color image in real-time. However, glossy, transparent or distant surface cannot be scanned properly by the sensor. As a result, enhancement and restoration from sensing depth is an important task. Depth completion aims at filling the holes that sensors fail to detect, which is still a complex task for machine to learn. Traditional hand-tuned methods have reached their limits, while neural network based methods tend to copy and interpolate the output from surrounding depth values. This leads to blurred boundaries, and structures of the depth map are lost. Consequently, our main work is to design an end-to-end network improving completion depth maps while maintaining edge clarity. We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced. In addition, we propose boundary consistency concept to enhance the depth map quality and structure. Experimental results validate the effectiveness of our self-attention and boundary consistency schema, which outperforms previous state-of-the-art depth completion work on Matterport3D dataset. Our code is publicly available at https://github.com/tsunghan-wu/Depth-Completion.