SpotActor: Training-Free Layout-Controlled Consistent Image Generation

Authors: Jiahao Wang, Caixia Yan, Weizhan Zhang, Haonan Lin, Mengmeng Wang, Guang Dai, Tieliang Gong, Hao Sun, Jingdong Wang

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments are conducted to demonstrate the effectiveness of our method. The results prove that Spot Actor fulfills the expectations of this task and showcases the potential for practical applications with superior layout alignment, subject consistency, prompt conformity and background diversity.
Researcher Affiliation Collaboration 1School of Computer Science and Technology, MOEKLINNS, Xi an Jiaotong University [...] 3College of Computer Science and Technology, Zhejiang University of Technology [...] 4SGIT AI Lab, State Grid Corporation of China [...] 5China Telecom Artificial Intelligence Technology Co.Ltd 6Baidu Inc
Pseudocode No The paper describes the method using textual descriptions, mathematical formulas, and architectural diagrams (Figure 2), but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No Project page https://johnneywang.github.io/Spot Actor-webpage/ . The paper provides a project page link, but it is not explicitly stated to be a code repository, nor is there an explicit statement about the release of source code for the methodology.
Open Datasets Yes We present Actor Bench, a specified benchmark with hundreds of reasonable prompt-box pairs stemming from object detection datasets. [...] we direct our focus on COCO2017 (Lin et al. 2014), a detection dataset of realworld photos.
Dataset Splits No We present Actor Bench, the first layout-to-consistent-image generation benchmark. It includes 100 single-subject sets and 100 double-subject sets. Every set consists of four prompt-box pairs of the same central subject(s). [...] We utilize the train set annotations to obtain naturally associated subject-box pairs. The paper describes the composition of its benchmark but does not provide specific training, validation, or test splits for its experiments.
Hardware Specification No The paper does not provide specific details about the hardware used for running its experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper mentions several models and frameworks (e.g., SDXL, U-Net, Grounded-SAM, DINO, CLIP, LPIPS) but does not provide specific version numbers for any software dependencies or libraries used in their implementation.
Experiment Setup No The paper describes the components of its proposed method, including nuanced layout energy function and attention mechanisms, and outlines the evaluation metrics. However, it does not explicitly provide concrete hyperparameter values (e.g., learning rate, batch size, epochs), optimizer settings, or other detailed training configurations used for its experiments.