# CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

arXiv: https://arxiv.org/abs/1911.05377 · HTML: https://mlsanity.com/paper/1911.05377/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2019.

## Built on by (most cited first, 30 of 110)

- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [CompletionFormer: Depth Completion with Convolutions and Vision Transformers](https://mlsanity.com/paper/2304.13030/) (2023)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://mlsanity.com/paper/2412.14015/) (2024)
- [Dynamic Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2202.09769/) (2022)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Bilateral Propagation Network for Depth Completion](https://mlsanity.com/paper/2403.11270/) (2024)
- [Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion](https://mlsanity.com/paper/2412.13389/) (2024)
- [LRRU: Long-short Range Recurrent Updating Networks for Depth Completion](https://mlsanity.com/paper/2310.08956/) (2023)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [Tri-Perspective View Decomposition for Geometry-Aware Depth Completion](https://mlsanity.com/paper/2403.15008/) (2024)
- [Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries](https://mlsanity.com/paper/2104.02253/) (2021)
- [Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects](https://mlsanity.com/paper/2110.00087/) (2021)
- [Learning Topology from Synthetic Data for Unsupervised Depth Completion](https://mlsanity.com/paper/2106.02994/) (2021)
- [Depth Anything with Any Prior](https://mlsanity.com/paper/2505.10565/) (2025)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [An Adaptive Framework for Learning Unsupervised Depth Completion](https://mlsanity.com/paper/2106.03010/) (2021)
- [OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration](https://mlsanity.com/paper/2411.19278/) (2024)
- [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning](https://mlsanity.com/paper/2112.06179/) (2021)
- [DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image](https://mlsanity.com/paper/2209.13362/) (2022)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Depth Completion using Plane-Residual Representation](https://mlsanity.com/paper/2104.07350/) (2021)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting](https://mlsanity.com/paper/2404.19758/) (2024)
- [OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations](https://mlsanity.com/paper/2406.11711/) (2024)
- [Bayesian Deep Basis Fitting for Depth Completion with Uncertainty](https://mlsanity.com/paper/2103.15254/) (2021)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion](https://mlsanity.com/paper/2204.13635/) (2022)
- [GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs](https://mlsanity.com/paper/2210.10758/) (2022)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)

## Abstract (arXiv)

Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resources needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as "context-aware CSPN", while weighted selection, "resource-aware CSPN" can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods.