Click2Mask: Local Editing with Dynamic Mask Generation
Authors: Omer Regev, Omri Avrahami, Dani Lischinski
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments demonstrate that Click2Mask not only minimizes user effort but also enables competitive or superior local image manipulations compared to So TA methods, according to both human judgement and automatic metrics. Key contributions include the simplification of user input, the ability to freely add objects unconstrained by existing segments, and the integration potential of our dynamic mask approach within other editing methods. |
| Researcher Affiliation | Academia | Omer Regev, Omri Avrahami, Dani Lischinski The Hebrew University of Jerusalem |
| Pseudocode | Yes | Our method is outlined in Algorithm 1 and illustrated in Figure 6. |
| Open Source Code | Yes | Project Page & Code https://omeregev.github.io/click2mask We look forward to users applying our method with the source code that is available in the project page (see Footnote in Page 1), either to edit images or to embed the method for generating or fine-tuning masks. |
| Open Datasets | Yes | Since we are unable to run Emu Edit ourselves, we must rely on the Emu Edit Benchmark (Sheynin et al. 2023), which includes images generated by Emu Edit. This benchmark contains images with several categories of editing instructions, such as adding objects, removing objects, altering style, etc. As our focus is adding objects to images, we filtered the dataset by the addition instruction. |
| Dataset Splits | No | This resulted in 533 items, from which we randomly sampled an evaluation subset of 100 samples. |
| Hardware Specification | No | The paper does not explicitly mention any specific hardware (like GPU or CPU models, or cloud instances) used for running the experiments. |
| Software Dependencies | No | The paper mentions several models and frameworks such as "Blended Latent Diffusion (BLD)", "Latent Diffusion Models (LDMs)", "Alpha-CLIP", "Stable Diffusion VAE", and "CLIP", but does not provide specific version numbers for any of the software dependencies used in their implementation. |
| Experiment Setup | No | The paper describes the methodological steps for dynamic mask evolution and evaluation criteria, but it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or other system-level training settings for their method. |