EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas

Luepol Pipanmekaporn, Kanabadee Srisomboon, Wilaiporn Lee, Akara Prayote

Machine Learning and Knowledge Extraction · 08.11.2026 · 8 (11) · 371

DOI: 10.3390/make8110371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 08.11.2026. Verfasst von Luepol Pipanmekaporn und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mobile mapping system (MMS) panoramas routinely capture the survey vehicle, which occludes a substantial portion of the road surface beneath the camera. Reconstructing this large missing region is challenging because of complex road textures, cast shadows, and illumination variations. Although GAN-based inpainting typically combines multiple loss terms to improve reconstruction quality, fixed loss weights cannot adapt to the evolving optimization requirements during training. This study proposes a quality-driven loss-balancing framework in which a Proximal Policy Optimization (PPO) controller dynamically adjusts auxiliary-loss weights. At each control step, the controller observes interval-level generator losses, the current loss weights, and training progress, and receives a reward derived from paired improvements in SSIM and LPIPS on a disjoint controller-feedback set. Because ground-truth training data are unavailable, training pairs are constructed by projecting the occluded region into a perspective viewport and retrieving the corresponding background from nearby panoramas using GPS and heading information. The framework is evaluated against Fixed-Weight training, SoftAdapt, and GradNorm on two real-world datasets, MMS-Urban and MMS-Suburban, using Pix2Pix and Big-LaMa backbones. Experimental results show that PPO-guided weight adaptation achieves the lowest FID across all four backbone–dataset configurations. Relative to Fixed-Weight training, it reduces LPIPS, MAE, and FID by 14.80%, 15.64%, and 20.65% on average, respectively, while improving SSIM by 4.08%, with less than 1% additional training time. Further comparisons with predefined monotonic scheduling and progress-only PPO demonstrate the backbone-dependent contribution of state-informed adaptive loss balancing, with clearer reconstruction improvements for Pix2Pix and limited additional benefits for Big-LaMa.

Zitieren

APA

Pipanmekaporn, L., Srisomboon, K., Lee, W., & Prayote, A. (2026). Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas. Machine Learning and Knowledge Extraction, 8(11), 371. https://doi.org/10.3390/make8110371

Vancouver

Pipanmekaporn L, Srisomboon K, Lee W, Prayote A. Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas. Machine Learning and Knowledge Extraction. 2026;8(11):371. doi:10.3390/make8110371

BibTeX
@article{Pipanmekaporn2026,
  author = {Pipanmekaporn, Luepol and Srisomboon, Kanabadee and Lee, Wilaiporn and Prayote, Akara},
  title = {Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {371},
  doi = {10.3390/make8110371}
}
Kostenlos starten →