# DeepForest: Sensing Into Self-Occluding Volumes of Vegetation With Aerial Imaging

arXiv: https://arxiv.org/abs/2502.02171 · HTML: https://mlsanity.com/paper/2502.02171/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 90 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [An Autonomous Drone for Search and Rescue in Forests using Airborne Optical Sectioning](https://mlsanity.com/paper/2105.04328/) (2021)
- [BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fields](https://mlsanity.com/paper/2306.03000/) (2023)
- [Search and Rescue with Airborne Optical Sectioning](https://mlsanity.com/paper/2009.08835/) (2020)
- [A Statistical View on Synthetic Aperture Imaging for Occlusion Removal](https://mlsanity.com/paper/1906.06600/) (2019)
- [Fast Automatic Visibility Optimization for Thermal Synthetic Aperture Visualization](https://mlsanity.com/paper/2005.04065/) (2020)
- [Pose Error Reduction for Focus Enhancement in Thermal Synthetic Aperture Visualization](https://mlsanity.com/paper/2012.08606/) (2020)
- [Combined Person Classification with Airborne Optical Sectioning](https://mlsanity.com/paper/2106.10077/) (2021)
- [Through-Foliage Tracking with Airborne Optical Sectioning](https://mlsanity.com/paper/2111.06959/) (2021)
- [Inverse Airborne Optical Sectioning](https://mlsanity.com/paper/2207.13344/) (2022)
- [Evaluation of Color Anomaly Detection in Multispectral Images For Synthetic Aperture Sensing](https://mlsanity.com/paper/2211.04293/) (2022)
- [Fusion of Single and Integral Multispectral Aerial Images](https://mlsanity.com/paper/2311.17515/) (2023)
- [Depth and DOF Cues Make A Better Defocus Blur Detector](https://mlsanity.com/paper/2306.11334/) (2023)
- [Stereoscopic Depth Perception Through Foliage](https://mlsanity.com/paper/2310.16120/) (2023)
- [A Novel Variational Approach for Multiphoton Microscopy Image Restoration: from PSF Estimation to 3D Deconvolution](https://mlsanity.com/paper/2311.18386/) (2023)

## Built on by (most cited first, 3 of 3)

- [Through-Foliage Surface-Temperature Reconstruction for Early Wildfire Detection](https://mlsanity.com/paper/2511.12572/) (2025)
- [How Robot Dogs See the Unseeable: Improving Visual Interpretability via Peering for Exploratory Robots](https://mlsanity.com/paper/2511.16262/) (2025)
- [Vision-Reasoning-Guided Occlusion Removal from Light Fields](https://mlsanity.com/paper/2606.19985/) (2026)

## Abstract (arXiv)

Access to below-canopy volumetric vegetation data is crucial for understanding ecosystem dynamics. We address the long-standing limitation of remote sensing to penetrate deep into dense canopy layers. LiDAR and radar are currently considered the primary options for measuring 3D vegetation structures, while cameras can only extract the reflectance and depth of top layers. Using conventional, high-resolution aerial images, our approach allows sensing deep into self-occluding vegetation volumes, such as forests. It is similar in spirit to the imaging process of wide-field microscopy, but can handle much larger scales and strong occlusion. We scan focal stacks by synthetic-aperture imaging with drones and reduce out-of-focus signal contributions using pre-trained 3D convolutional neural networks with mean squared error (MSE) as the loss function. The resulting volumetric reflectance stacks contain low-frequency representations of the vegetation volume. Combining multiple reflectance stacks from various spectral channels provides insights into plant health, growth, and environmental conditions throughout the entire vegetation volume. Compared with simulated ground truth, our correction leads to ~x7 average improvements (min: ~x2, max: ~x12) for forest densities of 220 trees/ha - 1680 trees/ha. In our field experiment, we achieved an MSE of 0.05 when comparing with the top-vegetation layer that was measured with classical multispectral aerial imaging.