Deep Domain Adversarial Adaptation for Photon-efficient Imaging Based on Spatiotemporal Inception Network

• URL: http://arxiv.org/abs/2201.02475v1
• Date: Fri, 7 Jan 2022 14:51:48 GMT
• Title: Deep Domain Adversarial Adaptation for Photon-efficient Imaging Based on Spatiotemporal Inception Network
• Authors: Yiwei Chen, Gongxin Yao, Yong Liu and Yu Pan
• Abstract summary: In single-photon LiDAR, photon-efficient imaging captures the 3D structure of a scene by only several signal detected per pixel. Existing deep learning models for this task are trained on simulated datasets, which poses the domain shift challenge when applied to realistic scenarios. We propose a network (STIN) for photon-efficient imaging, which is able to precisely predict the depth from a sparse and high-noise photon counting histogram by fully exploiting spatial and temporal information.
• Score: 11.58898808789911
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In single-photon LiDAR, photon-efficient imaging captures the 3D structure of a scene by only several detected signal photons per pixel. The existing deep learning models for this task are trained on simulated datasets, which poses the domain shift challenge when applied to realistic scenarios. In this paper, we propose a spatiotemporal inception network (STIN) for photon-efficient imaging, which is able to precisely predict the depth from a sparse and high-noise photon counting histogram by fully exploiting spatial and temporal information. Then the domain adversarial adaptation frameworks, including domain-adversarial neural network and adversarial discriminative domain adaptation, are effectively applied to STIN to alleviate the domain shift problem for realistic applications. Comprehensive experiments on the simulated data generated from the NYU~v2 and the Middlebury datasets demonstrate that STIN outperforms the state-of-the-art models at low signal-to-background ratios from 2:10 to 2:100. Moreover, experimental results on the real-world dataset captured by the single-photon imaging prototype show that the STIN with domain adversarial training achieves better generalization performance compared with the state-of-the-arts as well as the baseline STIN trained by simulated data.

Related papers

• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization [56.95046107046027]
  We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for scene coordinate regression. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain.
  arXiv  Detail & Related papers  (2023-10-10T20:11:13Z)
• Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
  We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
  arXiv  Detail & Related papers  (2023-03-17T18:00:27Z)
• A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas [10.477070348391079]
  We show that light-weight neural networks can be trained to perform the tomographic inversion with a single feed-forward pass. We train our encoder-decoder network using simulated data and validate our technique on real L-band and P-band data.
  arXiv  Detail & Related papers  (2023-01-20T14:34:03Z)
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World [83.36195426897768]
  We propose VRVO, a novel framework for retrieving the absolute scale from virtual data. We first train a scale-aware disparity network using both monocular real images and stereo virtual data. The resulting scale-consistent disparities are then integrated with a direct VO system.
  arXiv  Detail & Related papers  (2022-03-11T01:51:54Z)
• Robust photon-efficient imaging using a pixel-wise residual shrinkage network [7.557893223548758]
  Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios. limited signal photon counts and high noises in the collected data have posed great challenges for predicting the depth image precisely. We propose a pixel-wise residual shrinkage network for photon-efficient imaging from high-noise data.
  arXiv  Detail & Related papers  (2022-01-05T05:08:12Z)
• Learning a Model-Driven Variational Network for Deformable Image Registration [89.9830129923847]
  VR-Net is a novel cascaded variational network for unsupervised deformable image registration. It outperforms state-of-the-art deep learning methods on registration accuracy. It maintains the fast inference speed of deep learning and the data-efficiency of variational model.
  arXiv  Detail & Related papers  (2021-05-25T21:37:37Z)
• Sparse Signal Models for Data Augmentation in Deep Learning ATR [0.8999056386710496]
  We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm. We exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting.
  arXiv  Detail & Related papers  (2020-12-16T21:46:33Z)
• Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation [16.99302954185652]
  It remains an open challenge to train deep convolutional neural networks (DCNNs) using only a small quantity of training samples. This paper explores an effective training data augmentation approach that can be employed to improve the overall DCNN performance.
  arXiv  Detail & Related papers  (2020-12-14T19:14:35Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.