arXiv cs.AI· Chanhwi Jeong, Dongmin You, Seungwook Kim·· 10 小时前AI 评分20
TOGBench:评测并提升航拍图像中的微小目标生成保真度
TOGBench: Benchmarking and Improving Tiny-Object Generation Fidelity in Aerial Imagery
AI 导读
TOGBench 是一个面向航拍图像的定量、目标级基准,专门评测微小目标(车辆、船只、飞机等仅占几个像素的目标)的生成保真度,弥补以往生成评测只看提示词遵循或人类偏好的空白。研究还提出两种简单的训练/推理期技术,提升 layout-to-image 生成器渲染小目标的能力,使其在 TOGBench 上的表现得到提高。该工作已被 WACV 2027 Round 2 接收。
正文 · 原文
Abstract:Advances in deep generative models now enable the synthesis of realistic imagery. However, aerial imagery is dominated by tiny objects, such as vehicles, ships, and aircraft, which occupy only a few pixels owing to the overhead, wide-area nature of aerial imaging. Existing generative models struggle substantially more with tiny objects than with larger ones. This limitation has been overlooked, as prior work on generative evaluation emphasizes prompt following or human preference rather than whether small objects are rendered faithfully. To address this gap, we introduce TOGBench, a quantitative, object-level benchmark for evaluating tiny-object generation fidelity in aerial imagery. We further propose two simple train-/inference-time techniques that improve the ability of layout-to-image generators to render small objects, raising their performance on TOGBench.
| Comments: | Accepted to WACV 2027 Round 2. 20 pages, 7 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23840 [cs.CV] |
| (or arXiv:2611.23840v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23840 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Seungwook Kim [view email]
[v1]
Wed, 18 Nov 2026 04:45:57 UTC (15,847 KB)
来源:arXiv cs.AI · arxiv.org