cs.CVNov 17, 2026

Segmentation-Guided Direct Capacity Estimation of Rooftop Photovoltaics from Aerial Imagery

Authors: Guibin Chen, Emma Fan, Yuzhang Lin

Organizations: Department of Electrical and Computer Engineering, New York University, New York, USA

Abstract

Distribution planners need installation-level inventories of rooftop photovoltaic (PV) capacity, but interconnection records may be incomplete or spatially aggregated. Conventional image-based estimators segment PV arrays, convert the mask to physical area, and multiply by an estimated power density, coupling capacity prediction to mask-derived area. We propose Direct Head, a segmentation-guided architecture that retains U-Net segmentation and soft-mask pooling while directly regressing nonnegative capacity from PV-region features and area descriptors. We evaluate three independent runs on 7,590 French rooftop installations under the original split and a department-based holdout. Relative to a parameter-matched area-density neural model, Direct Head reduces mean absolute error by 8.7% and 12.5%, and symmetric mean absolute percentage error by 14.0% and 20.7%, respectively. Comparisons with conventional estimators, controlled architecture variants, auxiliary-loss ablations, and representative cases show that segmentation provides useful spatial evidence without requiring capacity to be determined by an area-density product.

Figures & tables

Explore similar work

Sep 14, 2026

Nationally Consistent, Locally Incomplete: A Bayesian Remote-Sensing Audit of Rooftop Photovoltaic Registries

Tracking the energy transition requires reliable statistics on renewable deployment. Rooftop photovoltaics (PV) are especially hard to track, owing to their decentralised nature, and the resulting inaccuracies in official statistics are known but not quantified. Remote sensing offers an independent way to identify rooftop PV systems. We introduce a Bayesian framework to estimate the ground-truth rooftop PV capacity from remote sensing detections, turning an imperfect detector into an uncertainty-aware measurement instrument. Applied to France, the corrected detections estimate a capacity of 4.03 GWp [3.96--4.11] (99% credible interval) of rooftop PV below 36 kWp, matching the transmission system operator's connection data within 3.3% nationally, while identifying local under-reports of up to 61% of local capacity. We also document and quantify a significant truncation bias in French rooftop PV open data. Beyond France, the approach paves the way for more reliable estimates of rooftop PV capacity worldwide.
Oct 30, 2026

An Empirical Study on Learning Rooftop Solar Potential from Satellite Imagery Directly Without Explicit Geometry

Rooftop solar potential estimation often relies on LiDAR, digital surface models (DSMs), or pipelines that explicitly reconstruct roof geometry before estimating solar potential. We propose Direct Rooftop Solar Prediction (DRSP), an end-to-end formulation that maps satellite imagery and coarse regional sunlight information directly to application-level solar outputs. DRSP neither requires explicit geometric representations as input nor predicts roof orientation, slope, height, DSMs, or other geometric quantities as intermediate outputs, and therefore requires no geometric intermediate supervision. To enable large-scale study of this formulation, we develop a programmatic data-curation pipeline that converts per-panel information from the Google Solar API into usable-rooftop masks and spatial solar-energy targets, yielding two geographically distinct datasets containing approximately 60K rooftops from the U.S. Midwest and 87K from Texas. We demonstrate the feasibility of DRSP and systematically characterize the effects of geographic training distribution, model depth, image resolution, regional sunlight conditioning, and heatmap regression objectives. Overall, our results suggest that useful rooftop-scale solar information can be learned directly from 2D imagery without explicit geometric intermediate representations, offering a simpler path toward large-scale solar assessment. Our code and dataset are available at https://github.com/joshualee124/direct_rooftop_solar_prediction.
Nov 3, 2026

High-fidelity training-free photovoltaic module mapping from multi-view UAV imagery

High-fidelity photovoltaic (PV) module mapping requires complete instance recovery and accurate delineation. Vision foundation models offer zero-shot segmentation, but converting incomplete and inconsistent predictions across views into a complete, geometrically accurate map of individual modules remains challenging. We propose the Multi-View PV Module Mapper (MV-PVMapper), a training-free framework coupling vision foundation models with unmanned aerial vehicle (UAV) photogrammetry. First, Segment Anything Model 3 (SAM 3) generates candidates from original images using text prompts. Their contours are then transferred into object space through per-module slope correction to limit distortion from surface-model noise, and verified against representative module dimensions to guide cross-view instance selection. Finally, accepted instances return to all covering images as box prompts for SAM~3, supplementing text prompts with spatial cues for iterative segmentation, verification and fusion. On five-direction surveys of three operational rooftop PV plants at approximately 1 cm nadir ground sampling distance, two feedback iterations recover 7,710 of 7,711 reference modules with no false positives at an intersection-over-union (IoU) matching threshold of 0.5. Macro-averaged area precision and recall reach 99.00 % and 98.52 %, respectively. Averaged across sites, the aggregated Jaccard index reaches 97.55 %, compared with 60.73 % and 41.24 % for orthomosaic segmentation and multi-view pixel-voting baselines, respectively; average precision at the stricter IoU threshold of 0.95 reaches 95.67 %. Ablation studies show that module-size constraints are critical for instance separation, while slope correction and feedback to all covering views improve boundary accuracy. These results are achieved without task-specific image annotation or segmentation-model weight updates.