mlsanityData to 14 Oct 2026

Depth Completion using Plane-Residual Representation

arXiv 2104.07350 ↗First posted 15 Apr 2021cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

The basic framework of depth completion is to predict a pixel-wise dense depth map using very sparse input data. In this paper, we try to solve this problem in a more effective way, by reformulating the regression-based depth estimation problem into a combination of depth plane classification and residual regression. Our proposed approach is to initially densify sparse depth information by figuring out which plane a pixel should lie among a number of discretized depth planes, and then calculate the final depth value by predicting the distance from the specified plane. This will help the network to lessen the burden of directly regressing the absolute depth information from none, and to effectively obtain more accurate depth prediction result with less computation power and inference time. To do so, we firstly introduce a novel way of interpreting depth information with the closest depth plane label p and a residual value r, as we call it, Plane-Residual (PR) representation. We also propose a depth completion network utilizing PR representation consisting of a shared encoder and two decoders, where one classifies the pixel's depth plane label, while the other one regresses the normalized distance from the classified depth plane. By interpreting depth information in PR representation and using our corresponding depth completion network, we were able to acquire improved depth completion performance with faster computation, compared to previous approaches.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

23 of 30 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  4. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  5. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  6. 2017Sparsity Invariant CNNscited by 326
  7. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  8. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  9. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  10. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
  11. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  12. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
11 more
  1. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  2. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
  3. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  4. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  5. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 110
  6. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  7. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  8. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  9. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  10. 2018Fast End-to-End Trainable Guided Filtercited by 50
  11. 2019Depth Coefficients for Depth Completioncited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 6; 2024: 4; 2025: 1; 2026: 1.

24 papers.

Sort:

By area:

  1. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  2. 2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
  3. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 49
  4. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  5. 2022SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completioncited by 23
  6. 2022GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNscited by 23
  7. 2022RGB-Depth Fusion GAN for Indoor Depth Completioncited by 18
  8. 2025Distilling Monocular Foundation Model for Fine-grained Depth Completioncited by 15
  9. 2022Depth Completion using Geometry-Aware Embeddingcited by 12
  10. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  11. 2023Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completioncited by 10
  12. 2024Learning to Control Camera Exposure via Reinforcement Learningcited by 9
12 more
  1. 2023AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completioncited by 8
  2. 2022MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Reportcited by 7
  3. 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completioncited by 7
  4. 2022Towards Domain-agnostic Depth Completioncited by 6
  5. 2023MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Resultscited by 4
  6. 2024DeCoTR: Enhancing Depth Completion with 2D and 3D Attentionscited by 4
  7. 2021Object-aware Monocular Depth Prediction with Instance Convolutionscited by 2
  8. 2024Progressive Depth Decoupling and Modulating for Flexible Depth Completioncited by 1
  9. 2022Confidence Guided Depth Completion Networkcited by 0
  10. 2022Spacecraft depth completion based on the gray image and the sparse depth mapcited by 0
  11. 2024Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completioncited by 0
  12. 2026ToFormer: Towards Large-scale Scenario Depth Completion for Lightweight ToF Cameracited by 0