mlsanityData to 7 Oct 2026

CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation

arXiv 2411.04480 ↗First posted 7 Nov 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Depth completion using lightweight time-of-flight (ToF) depth sensors is attractive due to their low cost. However, lightweight ToF sensors usually have a limited field of view (FOV) compared with cameras. Thus, only pixels in the zone area of the image can be associated with depth signals. Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone. To this end, this paper proposes the CFPNet to achieve cross-zone feature propagation from the zone area to the outside-zone area with two novel modules. The first is a direct-attention-based propagation module (DAPM), which enforces direct cross-zone feature acquisition. The second is a large-kernel-based propagation module (LKPM), which realizes cross-zone feature propagation by utilizing convolution layers with kernel sizes up to 31. CFPNet achieves state-of-the-art (SOTA) depth completion performance by combining these two modules properly, as verified by extensive experimental results on the ZJU-L5 dataset. The code is available at https://github.com/denyingmxd/CFPNet.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 7 Nov 2024.

Builds on

37 of 46 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016Layer Normalizationcited by 5,579
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  12. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
25 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  3. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  4. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  5. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  6. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  7. 2019Attention Augmented Convolutional Networkscited by 363
  8. 2017Sparsity Invariant CNNscited by 325
  9. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  10. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  11. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  12. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  13. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  14. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  15. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  16. 2021T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesiscited by 88
  17. 2021Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baselinecited by 61
  18. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  19. 2023Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensorcited by 30
  20. 2022DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Imagecited by 26
  21. 2022Consistent Direct Time-of-Flight Video Depth Super-Resolutioncited by 16
  22. 2023Digging into Depth Priors for Outdoor Neural Radiance Fieldscited by 11
  23. 2024RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methodscited by 8
  24. 2022MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Reportcited by 7
  25. 2017Sparse Depth Sensing for Resource-Constrained Robotscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Imagecited by 3
  2. 2025ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Networkcited by 1
  3. 2025DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidancecited by 1
  4. 2026On-Device Super Resolution Imaging Using Low-Cost SPAD Array and Embedded Lightweight Deep Learningcited by 0