RTLViT: real-time lensless reconstruction with a lightweight vision transformer
Abstract
Mask-based lensless imagers capture measurements using simple, compact hardware and recover images using a reconstruction algorithm. The reconstruction algorithm affects the image quality, inference speed, and computational requirements of the imaging system, often trading off image quality against computational efficiency. Advancing toward integrated lensless imagers, where encoding and reconstruction occur within a single device (e.g., a mobile phone), requires a fast, high-quality, and practical reconstruction method. We introduce the Real-Time Lensless Vision Transformer (RTLViT), a lightweight, purely data-driven reconstruction architecture for high-quality and real-time lensless reconstruction. With only 1.09 million learnable parameters, RTLViT provides higher-quality reconstructions than both real-time baselines and substantially larger attention-based architectures, including improvements of up to 3.46 dB in peak signal-to-noise ratio over architectures with 15 × more learnable parameters. We demonstrate that RTLViT maintains high-quality reconstructions across a wide range of training dataset sizes and two different mask designs (lenslets and a diffuser). Finally, we implement real-time reconstruction with RTLViT on laptops and smartphones, supporting future integrated lensless imagers for real-time applications.
Related
- Reference-free per-measurement assessment of lensless reconstruction quality under imperfect PSF models
- Role of Spatial Coherence in Single-Shot Lensless Image Reconstruction
- Continuous vision transformer-based neural operator for scalable beam propagation modeling in optical fibers
- Variational study of the magnetization plateaus in the spin-1/2 kagome Heisenberg antiferromagnet: An approach from vision transformer neural quantum states
- Efficient SPAD reconstruction framework with time-frequency domain compression and lightweight joint depth-intensity optimization
BibTeX
@misc{kabuli2026rtlvit,
title = {{RTLViT: real-time lensless reconstruction with a lightweight vision transformer}},
author = {Leyla A. Kabuli and Vasilisa Ponomarenko and Laura Waller},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21042},
eprint = {2609.21042},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21042},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - RTLViT: real-time lensless reconstruction with a lightweight vision transformer
AU - Leyla A. Kabuli
AU - Vasilisa Ponomarenko
AU - Laura Waller
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.21042
UR - https://arxiv.org/abs/2609.21042
AB - Mask-based lensless imagers capture measurements using simple, compact hardware and recover images using a reconstruction algorithm. The reconstruction algorithm affects the image quality, inference speed, and computational requirements of the imaging system, often trading off image quality against computational efficiency. Advancing toward integrated lensless imagers, where encoding and reconstruction occur within a single device (e.g., a mobile phone), requires a fast, high-quality, and practical reconstruction method. We introduce the Real-Time Lensless Vision Transformer (RTLViT), a lightweight, purely data-driven reconstruction architecture for high-quality and real-time lensless reconstruction. With only 1.09 million learnable parameters, RTLViT provides higher-quality reconstructions than both real-time baselines and substantially larger attention-based architectures, including improvements of up to 3.46 dB in peak signal-to-noise ratio over architectures with 15 × more learnable parameters. We demonstrate that RTLViT maintains high-quality reconstructions across a wide range of training dataset sizes and two different mask designs (lenslets and a diffuser). Finally, we implement real-time reconstruction with RTLViT on laptops and smartphones, supporting future integrated lensless imagers for real-time applications.
ER -