From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy

TL;DR

This paper introduces a new dataset and novel self-supervised and physically grounded methods for 3D reconstruction in light field microscopy, significantly improving image quality and data efficiency.

Contribution

It presents the XLFM-Zebrafish benchmark, MVN-LF for angular prior learning, and ORC Loss for physics-based consistency, advancing XLFM reconstruction techniques.

Findings

Improved PSNR by 7.7% over baselines

Introduced a large-scale XLFM dataset

Enhanced data efficiency with self-supervised learning

Abstract

Light field microscopy (LFM) has become an emerging tool in neuroscience for large-scale neural imaging in vivo, notable for its single-exposure volumetric imaging, broad field of view, and high temporal resolution. However, learning-based 3D reconstruction in XLFM remains underdeveloped due to two core challenges: the absence of standardized datasets and the lack of methods that can efficiently model its angular-spatial structure while remaining physically grounded. We address these challenges by introducing three key contributions. First, we construct the XLFM-Zebrafish benchmark, a large-scale dataset and evaluation suite for XLFM reconstruction. Second, we propose Masked View Modeling for Light Fields (MVN-LF), a self-supervised task that learns angular priors by predicting occluded views, improving data efficiency. Third, we formulate the Optical Rendering Consistency Loss (ORC Loss), a differentiable rendering constraint that enforces alignment between predicted volumes and their PSF-based forward projections. On the XLFM-Zebrafish benchmark, our method improves PSNR by 7.7% over state-of-the-art baselines.