# Dual-Attention Based 3D Channel Estimation

arXiv: https://arxiv.org/abs/2604.01769 · HTML: https://mlsanity.com/paper/2604.01769/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Deep Learning-Based Channel Estimation](https://mlsanity.com/paper/1810.05893/) (2018)
- [DeepRx: Fully Convolutional Deep Learning Receiver](https://mlsanity.com/paper/2005.01494/) (2020)
- [End-to-end Learning for OFDM: From Neural Receivers to Pilotless Communication](https://mlsanity.com/paper/2009.05261/) (2020)
- [Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Training](https://mlsanity.com/paper/2302.04368/) (2023)
- [RCNet: Incorporating Structural Information into Deep RNN for MIMO-OFDM Symbol Detection with Limited Training](https://mlsanity.com/paper/2003.06923/) (2020)
- [Low-complexity Near-optimum Symbol Detection Based on Neural Enhancement of Factor Graphs](https://mlsanity.com/paper/2203.16417/) (2022)
- [Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO Systems with Low-Density Pilots](https://mlsanity.com/paper/2303.00986/) (2023)
- [Graph Neural Network Aided Expectation Propagation Detector for MU-MIMO Systems](https://mlsanity.com/paper/2201.03731/) (2022)
- [Learning to Search for MIMO Detection](https://mlsanity.com/paper/1909.07858/) (2019)
- [Soft MIMO Detection Using Marginal Posterior Probability Statistics](https://mlsanity.com/paper/2208.08045/) (2022)

## Built on by (most cited first, 1 of 1)

- [Optimal Power Allocation and AI Receiver Design for Superimposed DMRS and Data Transmission](https://mlsanity.com/paper/2608.13809/) (2026)

## Abstract (arXiv)

For multi-input and multi-output (MIMO) channels, the optimal channel estimation (CE) based on linear minimum mean square error (LMMSE) requires three-dimensional (3D) filtering. However, the complexity is often prohibitive due to large matrix dimensions. Suboptimal estimators approximate 3DCE by decomposing it into time, frequency, and spatial domains, while yields noticeable performance degradation under correlated MIMO channels. On the other hand, recent advances in deep learning (DL) can explore channel correlations in all domains via attention mechanisms. Building on this capability, we propose a dual attention mechanism based 3DCE network (3DCENet) that can achieve accurate estimates.