# ESAR: Event-Based Synthetic Aperture Reconstruction

arXiv: https://arxiv.org/abs/2607.15073 · HTML: https://mlsanity.com/paper/2607.15073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy](https://mlsanity.com/paper/2009.08283/) (2020)
- [Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1811.08230/) (2018)
- [Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow](https://mlsanity.com/paper/2112.06242/) (2021)
- [Bilevel Inverse Problems in Neuromorphic Imaging](https://mlsanity.com/paper/2302.02052/) (2023)
- [Dynamic Reconstruction from Neuromorphic Data](https://mlsanity.com/paper/2408.15465/) (2024)

## Abstract (arXiv)

Event cameras report asynchronous polarity events when changes in log--radiance exceed a fixed contrast threshold, producing signed temporal contrast measurements rather than conventional image frames. We formulate monocular event-based imaging as a synthetic-aperture inverse problem for a static ground-domain log--radiance field θ ∈ ℝNg. Instead of reconstructing a latent pixel-time volume v ∈ ℝNpNt, we impose the geometric relation v=Pθ, where P maps the fixed scene into motion-dependent latent views. Aggregating events over finite time intervals gives the linearized model [ APθ = b+η, ] where A is a temporal differencing operator, b contains signed binned event counts, and η represents measurement and modeling errors. This decomposition exposes a synthetic-aperture structure: under near-nadir motion, successive projections are approximately shifted views of a common scene, while the composite operator AP remains ill-conditioned because it combines spatial averaging with temporal differencing. We therefore use regularized inversion to recover θ. Numerical experiments on simulated data and real near-nadir Falcon Neuro event data show that the proposed θ-based formulation recovers coherent large-scale spatial structure, relative to dynamic latent-image and learned event-reconstruction baselines, while suppressing fine-scale texture.