# Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

arXiv: https://arxiv.org/abs/2403.15008 · HTML: https://mlsanity.com/paper/2403.15008/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 63 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 30 of 46)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [Learning Depth with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1810.02695/) (2018)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [Learning Guided Convolutional Network for Depth Completion](https://mlsanity.com/paper/1908.01238/) (2019)
- [CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion](https://mlsanity.com/paper/1911.05377/) (2019)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds](https://mlsanity.com/paper/2012.09242/) (2020)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [CompletionFormer: Depth Completion with Convolutions and Vision Transformers](https://mlsanity.com/paper/2304.13030/) (2023)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Learning Affinity via Spatial Propagation Networks](https://mlsanity.com/paper/1710.01020/) (2017)
- [Sparse and noisy LiDAR completion with RGB guidance and uncertainty](https://mlsanity.com/paper/1902.05356/) (2019)
- [Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation](https://mlsanity.com/paper/1808.00769/) (2018)
- [Learning Joint 2D-3D Representations for Depth Completion](https://mlsanity.com/paper/2012.12402/) (2020)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Dynamic Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2202.09769/) (2022)
- [Adaptive Context-Aware Multi-Modal Network for Depth Completion](https://mlsanity.com/paper/2008.10833/) (2020)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark](https://mlsanity.com/paper/2108.03830/) (2021)
- [Confidence Propagation through CNNs for Guided Sparse Depth Regression](https://mlsanity.com/paper/1811.01791/) (2018)
- [PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2308.16896/) (2023)

## Built on by (most cited first, 30 of 42)

- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion](https://mlsanity.com/paper/2412.13389/) (2024)
- [Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer](https://mlsanity.com/paper/2407.19628/) (2024)
- [DepthLab: From Partial to Complete](https://mlsanity.com/paper/2412.18153/) (2024)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [Language Driven Occupancy Prediction](https://mlsanity.com/paper/2411.16072/) (2024)
- [Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction](https://mlsanity.com/paper/2409.07972/) (2024)
- [Distilling Monocular Foundation Model for Fine-grained Depth Completion](https://mlsanity.com/paper/2503.16970/) (2025)
- [DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution](https://mlsanity.com/paper/2410.11666/) (2024)
- [VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection](https://mlsanity.com/paper/2506.04623/) (2025)
- [DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain](https://mlsanity.com/paper/2410.14980/) (2024)
- [Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion](https://mlsanity.com/paper/2412.19225/) (2024)
- [WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion](https://mlsanity.com/paper/2504.13561/) (2025)
- [DuCos: Duality Constrained Depth Super-Resolution via Foundation Model](https://mlsanity.com/paper/2503.04171/) (2025)
- [VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction](https://mlsanity.com/paper/2506.05563/) (2025)
- [SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps](https://mlsanity.com/paper/2409.10202/) (2024)
- [Amodal Depth Anything: Amodal Depth Estimation in the Wild](https://mlsanity.com/paper/2412.02336/) (2024)
- [Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow](https://mlsanity.com/paper/2503.06992/) (2025)
- [Event-Driven Dynamic Scene Depth Completion](https://mlsanity.com/paper/2505.13279/) (2025)
- [Structure-Aware Radar-Camera Depth Estimation](https://mlsanity.com/paper/2506.05008/) (2025)
- [PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency](https://mlsanity.com/paper/2507.07374/) (2025)
- [Large Depth Completion Model from Sparse Observations](https://mlsanity.com/paper/2605.30115/) (2026)
- [Diff-Reg v1: Diffusion Matching Model for Registration Problem](https://mlsanity.com/paper/2403.19919/) (2024)
- [DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image](https://mlsanity.com/paper/2504.01596/) (2025)
- [Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor](https://mlsanity.com/paper/2409.08277/) (2024)
- [Learning Inverse Laplacian Pyramid for Progressive Depth Completion](https://mlsanity.com/paper/2502.07289/) (2025)
- [Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion](https://mlsanity.com/paper/2508.04984/) (2025)
- [AURORA-KITTI: Any-Weather Depth Completion and Denoising](https://mlsanity.com/paper/2603.14701/) (2026)
- [STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene](https://mlsanity.com/paper/2506.23157/) (2025)

## Abstract (arXiv)

Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. However, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this challenge, we introduce Tri-Perspective view Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPV affinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Furthermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sensor and the color camera on smartphones. Project page: https://yanzq95.github.io/projectpage/TOFDC/index.html