HFPC combines a BLIP-based reward model trained on 44,000 human-annotated product inpainting images with a segmentation-based product consistency check to automatically filter low-quality generated images, reporting 96.4% precision on its own test set.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Evaluation Framework for Product Images Background Inpainting based on Human Feedback and Product Consistency
HFPC combines a BLIP-based reward model trained on 44,000 human-annotated product inpainting images with a segmentation-based product consistency check to automatically filter low-quality generated images, reporting 96.4% precision on its own test set.