Stabilizing Holistic Semantics in Diffusion Bridge for Image Inpainting

Authors: Jinjia Peng, Mengkai Li, Huibing Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on Places2, Paris Street View and Celeb A-HQ datasets validate the efficacy of the proposed method.
Researcher Affiliation Academia 1School of Cyber Security and Computer, Hebei University, China 2College of Information Science and Technology, Dalian Maritime University, China EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes the methodology using mathematical equations and textual explanations, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link indicating the availability of open-source code for the described methodology.
Open Datasets Yes We validate our method and various baselines on three typical datasets, including Paris Street View (PSV) [Doersch et al., 2012], ...; Celeb A-HQ [Karras et al., 2018] ...; Places2 [Zhou et al., 2017] is a collection of more than 1.8 million natural images in multiple scenes.
Dataset Splits Yes Paris Street View (PSV) [Doersch et al., 2012], which consists of street photos taken in Paris and contains 14,900 training images and 100 validation images; Celeb A-HQ [Karras et al., 2018] is a dataset containing 30,000 high-quality human face images, divided into 28k training images and 2k validation images;
Hardware Specification No The paper does not provide specific hardware details (such as GPU/CPU models, processor types, or memory amounts) used for running the experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes where the parameter a is set to 5 for all experiments. ... In Figure 7, we set Α to take values at [0.2T, 0.4T, 0.6T, 0.8T] to evaluate its effect on the final inpainted results. ... we finally choose Α = 0.6T, as the stage point for phased injection of guidance information.