Problem
Research questions and friction points this paper is trying to address.
relative object scale
image generation
image editing
GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
🤖 AI Summary
为解决图像生成和编辑中物体相对大小不真实的问题，本文引入了GenScale基准测试，并设计了Rescale后处理代理来修正局部尺度。
📝 Abstract
Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure this failure mode, we introduce GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing. GenScale contains 900 image-level entries and 1,643 pairwise anchor-target scale relations across common-object generation, human-product generation with metric dimensions, and scale correction from failed generations. We further design a human-calibrated ordinal judge for scalable pairwise scale evaluation. Last but not the least, we introduce Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator. Experiments reveal that state-of-the-art image generators and editors cannot reliably observe relative scale yet, while Rescale consistently improves scale plausibility across generated and edited images. Together, GenScale establishes relative object scale as a distinct, measurable, and actionable capability for image generation systems.
Innovation
Methods, ideas, or system contributions that make the work stand out.
relative object scale
image generation and editing
GenScale
human-calibrated ordinal judge
Rescale
🔎 Similar Papers
No similar papers found.
