Unsupervised Region-Based Image Editing of Denoising Diffusion Models
Authors: Zixiang Li, Yue Song, Renshuai Tao, Xiaohong Jia, Yao Zhao, Wei Wang
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conducted extensive experiments across multiple datasets and various architectures of diffusion models, achieving state-of-the-art performance. Extensive experiments and comprehensive evaluations validate the effectiveness of our proposed method. We conduct experiments on the datasets Celeb A-HQ (Liu et al. 2015), LSUN-church (Yu et al. 2015), LSUN-bedroom (Yu et al. 2015), and the diffusion model architectures DDPM and i DDPM (Nichol and Dhariwal 2021). |
| Researcher Affiliation | Academia | Zixiang Li1,2, Yue Song4, Renshuai Tao1,2, Xiaohong Jia5, Yao Zhao1,2,3*, Wei Wang1,2* 1Institute of Information Science, Beijing Jiaotong University 2Visual Intellgence +X International Cooperation Joint Laboratory of MOE 3Pengcheng Laboratory, Shenzhen, China 4University of Trento, Italy 5Lanzhou Jiaotong University |
| Pseudocode | No | The paper describes its methodology using mathematical formulations and textual descriptions, but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about open-sourcing their code or a link to a code repository. It mentions "All algorithms and specific experimental settings can be found in the appendix," but this does not confirm code availability. |
| Open Datasets | Yes | We conduct experiments on the datasets Celeb A-HQ (Liu et al. 2015), LSUN-church (Yu et al. 2015), LSUN-bedroom (Yu et al. 2015) |
| Dataset Splits | No | We randomly select 500 images on Celeba HQ for testing. This provides a test set size but not the full training/validation/test splits or a detailed methodology for partitioning the datasets. |
| Hardware Specification | Yes | All our experiments can be performed on a single RTX 3090 GPU. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The paper states, "All algorithms and specific experimental settings can be found in the appendix," but the appendix is not provided in the main text. Therefore, specific hyperparameter values (e.g., learning rate, batch size, epochs, optimizer settings) are not detailed within the provided paper content. |