mlsanityData to 7 Oct 2026

Video super-resolution for single-photon LIDAR

arXiv 2210.10474 ↗First posted 19 Oct 2022eess.IV cs.CV physics.opticscited by 3

Not on the map. Why?

Abstract (arXiv)

3D Time-of-Flight (ToF) image sensors are used widely in applications such as self-driving cars, Augmented Reality (AR) and robotics. When implemented with Single-Photon Avalanche Diodes (SPADs), compact, array format sensors can be made that offer accurate depth maps over long distances, without the need for mechanical scanning. However, array sizes tend to be small, leading to low lateral resolution, which combined with low Signal-to-Noise Ratio (SNR) levels under high ambient illumination, may lead to difficulties in scene interpretation. In this paper, we use synthetic depth sequences to train a 3D Convolutional Neural Network (CNN) for denoising and upscaling (x4) depth data. Experimental results, based on synthetic as well as real ToF data, are used to demonstrate the effectiveness of the scheme. With GPU acceleration, frames are processed at >30 frames per second, making the approach suitable for low-latency imaging, as required for obstacle avoidance.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 17 of its 44 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

17 of 44 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  3. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  4. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  5. 2020Understanding SSIMcited by 75
  6. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  7. 2020Video Super Resolution Based on Deep Learning: A Comprehensive Surveycited by 54
  8. 2016A Formal Evaluation of PSNR as Quality Measurement Parameter for Image Segmentation Algorithmscited by 42
  9. 2021Generalized Huber Loss for Robust Learning and its Efficient Minimization for a Robust Statisticscited by 32
  10. 2021BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimationcited by 31
  11. 2020An Overview of Depth Cameras and Range Scanners Based on Time-of-Flight Technologiescited by 20
  12. 2020iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networkscited by 9
5 more
  1. 2019Spatial images from temporal datacited by 7
  2. 2020Robust super-resolution depth imaging via a multi-feature fusion deep networkcited by 7
  3. 2021High-speed object detection with a single-photon time-of-flight image sensorcited by 7
  4. 2016Deep Depth Super-Resolution : Learning Depth Super-Resolution using Deep Convolutional Neural Networkcited by 4
  5. 2022A direct time-of-flight image sensor with in-pixel surface detection and dynamic visioncited by 4

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025A Survey of Deep Learning Video Super-Resolutioncited by 5
  2. 2025Point upsampling networks for single-photon sensingcited by 0
  3. 2025Hardware-aware Coding Function Design for Compressive Single-Photon 3D Camerascited by 0