Skip to content
Preprint

GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing

Sep 2026 · 1 citation · ⚡ 1 influential · 60 references
Computer Science

TL;DR

This work introduces GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing, and introduces Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator.

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.

View source

Similar papers

Preprint Sep 2026

Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System

Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve who or what is being depicted. When generating or editing images of a specific subject, identity may drift as the pose, expression, appearance, viewpoint, or surroundi...

Meng-Wei Ren, Xuan-Er Zhang, Zhi-Hao Xia · 0 citations
#artificial intelligence Preprint Sep 2026

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paint-Anything is presented, which learns a shared hex-prompt interface for generation and editing through object-level color supervision, and introduces Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks.

Ji Xie, Dewei Zhou, Xin-Yu Huang et al. · 0 citations
Preprint Sep 2026

GenPuzzle: Benchmarking Visual Reasoning in Image Generation Models

GenPuzzle provides a testbed for measuring progress from image rendering toward visual problem solving, and uses task-specific evaluation protocols that select the automatic judge by measuring agreement with human reference scores.

Chang-Peng Zhao, Yi-Ren Song, Jin-Peng Wang · 3 citations
Preprint Aug 2026

PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes

PoseAdapter, a lightweight framework for high-fidelity 2.5D controllable image generation, and a Context-Aware Dual-Stream Representation, to resolve the generative trade-off between strict instance isolation and global coherence.

Yu-Feng Chi, Hui-Min Ma, Fan Gao et al. · 0 citations
Preprint Aug 2026

Mover360: Controllable Object Manipulation in 360{\deg} Panoramic Images

We present Mover360, a controllable object manipulation framework for 360{\deg} images. Unlike perspective images, 360{\deg} images in equirectangular projection (ERP) exhibit horizontal wrap-around, latitude-dependent distortion, and global scene continuity, which makes object-level edits difficult for existing perspe...

Haoyi Zhong, Fang-Lue Zhang, Andrew Chalmers et al. · 0 citations
Preprint Aug 2026

Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation

Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment, overlooking whether a generator forms a stable 3D interpretation and produces assets usable in graphics pipelines. We introduce Cyc3D, a multidimensional benchmark tha...

Li-Wen Zhang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.