paper-with-me

Layout-to-Image Generation

11개 벤치마크 · 논문 50편 · 이 태스크의 논문 보기 →

Benchmarks

COCO-Stuff 128x128

결과 5개

COCO-Stuff 256x256

결과 5개

COCO-Stuff 64x64

결과 5개

Visual Genome 128x128

결과 5개

Visual Genome 256x256

결과 4개

Visual Genome 64x64

결과 4개

LayoutBench

결과 3개

Most implemented

Image Generation from Scene Graphs

2018-04-04 · 구현 4개

Papers

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

2026-08-21 · Wenyang Hong, Yuan Wang, Yanbin Hao, Lanqing Xue 외 arxiv

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 additi…

Layout-to-Image Generation

Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

2026-05-29 · Nan Bao, Yifan Zhao, Wenzhuang Wang, Jia Li arxiv

The layout-to-image (L2I) task enables fine-grained control over image generation via object categories and spatial layouts. However, existing L2I methods yield fragmented and distorted generations under few-shot atypica…

Layout-to-Image Generation

Visual Prototype Conditioned Focal Region Generation for UAV-Based Object Detection

2026-04-03 · Wenhao Li, Zimeng Wu, Yu Wu, Zehua Fu 외 arxiv

Unmanned aerial vehicle (UAV) based object detection is a critical but challenging task, when applied in dynamically changing scenarios with limited annotated training data. Layout-to-image generation approaches have pro…

Layout-to-Image GenerationObject Detection

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

2026-03-18 · Kai Zou, Hongbo Liu, Dian Zheng, Jianxiong Gao 외 arxiv

In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to text descriptions (e.g., spatial relations…

Layout-to-Image Generation

Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers

2025-11-11 · Sida Huang, Siqi Huang, Ping Luo, Hongyuan Zhang arxiv

With the development of diffusion models, enhancing spatial controllability in text-to-image generation has become a vital challenge. As a representative task for addressing this challenge, layout-to-image generation aim…

Layout-to-Image GenerationText-to-Image Generation

TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation

2025-10-24 · Datao Tang, Hao Wang, Yudeng Xin, Hui Qiao 외 arxiv

Remote sensing vision tasks require extensive labeled data across multiple, interconnected domains. However, current generative data augmentation frameworks are task-isolated, i.e., each vision task requires training an …

Layout-to-Image GenerationData Augmentation

전체 50편 보기 →