# DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation

arXiv: https://arxiv.org/abs/2508.08900 · HTML: https://mlsanity.com/paper/2508.08900/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [A Benchmark and a Baseline for Robust Multi-view Depth Estimation](https://mlsanity.com/paper/2209.06681/) (2022)
- [Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields](https://mlsanity.com/paper/2106.03043/) (2021)
- [Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability](https://mlsanity.com/paper/2207.12939/) (2022)
- [MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2210.07577/) (2022)
- [Towards agricultural autonomy: crop row detection under varying field conditions using deep learning](https://mlsanity.com/paper/2109.08247/) (2021)
- [Rapid Light Field Depth Estimation with Semi-Global Matching](https://mlsanity.com/paper/1907.13449/) (2019)
- [Fast and Efficient Depth Map Estimation from Light Fields](https://mlsanity.com/paper/1805.00264/) (2018)

## Abstract (arXiv)

Dense light field depth estimation remains challenging due to sparse angular sampling, occlusion boundaries, textureless regions, and the cost of exhaustive multi-view matching. We propose Deep Spectral Epipolar Representation (DSER), a geometry-aware framework that introduces spectral regularization in the epipolar domain for dense disparity reconstruction. DSER models frequency-consistent EPI structure to constrain correspondence estimation and couples this prior with a hybrid inference pipeline that combines least squares gradient initialization, plane-sweeping cost aggregation, and multiscale EPI refinement. An occlusion-aware directed random walk further propagates reliable disparity along edge-consistent paths, improving boundary sharpness and weak-texture stability. Experiments on benchmark and real-world light field datasets show that DSER achieves a strong accuracy-efficiency trade-off, producing more structurally consistent depth maps than representative classical and hybrid baselines. These results establish spectral epipolar regularization as an effective inductive bias for scalable and noise-robust light field depth estimation.