OccluRank: Controllable Occlusion-Aware Layout-to-Image Generation by Adding Just an Ordinal Rank

📅 2026-08-21
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
为解决布局到图像生成中的遮挡顺序问题,提出OccluRank方法,通过添加序数排名来控制遮挡顺序,并使用Order-aware Instance Interaction模块优化实例间的交互。
📝 Abstract
Layout-to-image generation enables explicit spatial control through bounding-box layouts, yet bounding boxes specify only instance locations and cannot represent their occlusion order. Existing methods may rely on additional geometric conditions, employ complex inference procedures, or aggregate independently constructed instance representations without explicitly modeling their occlusion-dependent interactions. We propose OccluRank, a simple and controllable occlusion-aware layout-to-image framework that augments each bounding box with only one ordinal rank. OccluRank encodes the user-specified occlusion order through lightweight rank-based conditioning and introduces an Order-aware Instance Interaction (OII) module to jointly update rank-conditioned instance representations before aggregation. This allows the specified order to guide information exchange among occluding instances without additional geometric inputs or specialized inference-time optimization. We further construct OccluLayout, a synthetic training dataset whose occlusion order and amodal annotations are derived directly from known scene geometry rather than estimated from partially occluded images using auxiliary prediction models. For comprehensive evaluation, we introduce OccluLayout-Bench, which uses multiple multimodal large language model evaluators to assess instance presence, spatial layout, attributes, and occlusion order, together with FID for overall image quality. Experiments show that OccluRank more reliably preserves target instances, follows specified layouts, and realizes desired occlusion relationships while maintaining comparable attribute consistency and overall image quality.
Problem

Research questions and friction points this paper is trying to address.

layout-to-image generation
occlusion order
bounding box
Innovation

Methods, ideas, or system contributions that make the work stand out.

OccluRank
ordinal rank
Order-aware Instance Interaction (OII)
OccluLayout
OccluLayout-Bench
💼 Related Jobs
No related jobs found.
W
Wenyang Hong
Hefei University of Technology
Y
Yuan Wang
School of Cyber Science and Technology, University of Science and Technology of China
Yanbin Hao
Yanbin Hao
Hefei University of Technology
Video retrievalvideo action recognitionhashingVideo Hyperlinking
L
Lanqing Xue
LCFC
K
Ke Wang
ByteDance Inc.
Xiang Wang
Xiang Wang
University of Science and Technology of China
Trustworthy AIGraph LearningRecommendationFoundation ModelsMultimodal Models
K
Kuien Liu
Hefei University of Technology; Institute of Software, Chinese Academy of Sciences
Richang Hong
Richang Hong
Hefei University of Technology
MultimediaPattern Recognition