- Rating
- 4(+2)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3(+2)
Read review
Paper summary
This paper introduces RefineEdit, a training-free image editing method based on GRN. It uses bitwise probability differences, source-anchored routing, and two mask stabilization mechanisms to balance editing effectiveness and content preservation. Experiments demonstrate strong background preservation and text alignment.
Critical strengths
- The paper presents a clear motivation for leveraging the iterative refinement process of GRN for image editing.
- RefineEdit introduces a straightforward editing framework based on bitwise probability differences and source-anchored routing, without requiring additional training, external masks, or attention manipulation.
- The method is well-motivated and demonstrates a promising balance between editing effectiveness and content preservation.
Critical weaknesses
- My main concern is the results primarily establish that GRN-generated images can be effectively edited through their refinement trajectories, rather than demonstrating general-purpose image editing capabilities. Because both PIE-Bench and EditEval v2 evaluations use GRN-generated source images rather than the original benchmark images, it limits the fairness of the comparisons and its applicability to any real images.
- The reported gains may partly stem from differences in the underlying generative backbones rather than the proposed editing strategy.
- This work lacks comparisons with recent binary/autoregressive image editing methods, such as AREdit, EditInfinity and BitResEdit, making it difficult to assess its advantages over closely related approaches.
Questions for authors
- Both PIE-Bench and EditEval v2 evaluations use GRN-generated source images rather than the original benchmark images. It is very important for the authors to clarify how RefineEdit could be extended to arbitrary real-world images?
- Could the authors compare the text-to-image generation capabilities of GRN and the baselines' backbones to clarify whether the reported editing improvements stem from the stronger generative backbone or the proposed editing method?
- Could the authors provide comparisons with recent binary/autoregressive image editing methods, such as AREdit, EditInfinity, and BitResEdit, to better establish the advantages of RefineEdit over closely related approaches?
4 comments
W3, Q2 and Q3: Backbone quality and comparisons with autoregressive editors
We measured GRN-2B on GenEval. Its overall score of 0.7036 is close to the published Infinity-2B score of 0.73, which uses prompt rewriting. FLUX.1-dev scores higher than GRN on counting and colors. In Table 1 of our paper, RefineEdit outperforms both FLUX.1-dev editors, FlowEdit and RF-Inversion, on all four background metrics and both CLIP scores.
Bold marks the best score and underline marks the next distinct score in both tables.
| GenEval metric↑ | Infinity-2B | GRN-2B (measured) | FLUX.1-dev | SD 1.4 | SD 1.5 |
|---|---|---|---|---|---|
| Single object | 0.9906 | 0.97 | 0.97 | ||
| Two objects | 0.85 | 0.81 | 0.39 | 0.38 | |
| Counting | 0.63 | 0.74 | 0.33 | 0.35 | |
| Colors | 0.83 | 0.7686 | 0.73 | 0.76 | |
| Position | 0.49 | 0.22 | 0.03 | 0.04 | |
| Color attribution | 0.57 | 0.57 | 0.05 | 0.06 | |
| Overall | 0.73 | 0.66 | 0.42 | 0.43 |
We also evaluated AREdit, BitResEdit, and EditInfinity on the GRN source images used for our editing comparison. All three baselines used Infinity-2B in our experiments.
| Method | Backbone | Structure Distance ↓ | PSNR ↑ | LPIPS ↓ | MSE ↓ | SSIM ↑ | CLIP Whole ↑ | CLIP Edited ↑ |
|---|---|---|---|---|---|---|---|---|
| AREdit | Infinity-2B | 0.02873 | 25.106 | 0.05867 | 0.008382 | 0.87782 | 26.424 | 23.057 |
| BitResEdit | Infinity-2B | 0.07388 | 26.94 | 0.0385 | 0.003232 | 0.93225 | 27.263 | 24.377 |
| EditInfinity | Infinity-2B | 0.07504 | 24.719 | 0.04163 | 0.005137 | 0.91609 | 26.867 | 24.201 |
| RefineEdit | GRN-2B | 0.02666 | 30.36 | 0.03178 | 0.004567 | 0.95037 | 26.597 | 23.447 |
Among the four editors, RefineEdit achieves the lowest Structure Distance (0.02666). It also achieves the highest background PSNR (30.36 dB), lowest background LPIPS (0.03178), and highest background SSIM (0.95037). It outperforms AREdit on all seven metrics. Appendix C also compares the two methods on the original PIE-Bench images, where RefineEdit improves PSNR over AREdit by 0.82 dB and SSIM from 0.8370 to 0.8669.
BitResEdit achieves the lowest MSE and the highest CLIP scores. Its external edit mask tells it where to apply the prompt, which may contribute to its higher CLIP scores. RefineEdit doesn't need external edit mask. EditInfinity optimizes a prompt embedding and fits LoRA weights for each input image. RefineEdit requires neither step. Including this optimization, EditInfinity took 2.2 times as long per image as RefineEdit on average in our measurements. Infinity-2B slightly outperforms GRN-2B on GenEval overall (0.73 vs. 0.7036). Despite this gap, RefineEdit outperforms all three Infinity-2B editors on Structure Distance, PSNR, LPIPS, and SSIM, demonstrating the effectiveness of its editing strategy in preserving scene structure and background detail.
I appreciate the authors’ response. The real-image editing demonstrations have eased my doubts about practical usability. I recommend adding comparisons and analyses with Infinity-based editing methods, given the relevant connections between the proposed method and this line of work. Specifically, I would prefer to see editing comparisons on the real-image of PIE-Bench instead of GRN-generated images. Furthermore, I believe comparisons with several state-of-the-art image editing models, such as FLUX.1 Kontext and Qwen-Image-Edit, could enrich the paper. Nevertheless, I view this editing method built upon the novel GRN architecture as a substantial contribution to the community, and it also exhibits promising performance on real-image editing tasks; I will therefore increase my score to 4.
Thank you very much for your positive update and thoughtful suggestions. We are pleased that our real-image editing demonstrations helped address your concerns. We hope our work can offer interesting insights to the community and inspire further explorations on training-free image editing models.
Thank you for your thoughtful review and suggestions. We have revised the manuscript and marked the changes in red for ease of content. Our point-by-point responses follow below.
Our main task is prompt to prompt editing. a common starting point is an image generated by the base model. RefineEdit reuses an intermediate GRN state from that generation run. Hu et al.[1] used a similar protocol for ISLock. LlamaGen generated the source images from PIE-Bench prompts, and Anchor Token Matching (ATM) used source tokens as anchors during editing. The diffusion and flow baselines receive the same RGB image generated by LlamaGen. In our comparison, every method edits the same GRN image with the same prompt and is scored against the same source. RefineEdit also has access to the source trajectory. Section 5.3 controls for that access.
Paper Appendix C extends RefineEdit to an real image editing given its source and editing prompts. We encode the image once with the frozen HBQ tokenizer and use its bits to construct a source reference at each refinement step. Selected bits follow the editing prompt, and unselected bits copy the reference. This lets us edit an image without its original generation trajectory or an inversion step.
We tested this extension on all 700 original PIE-Bench images. RefineEdit achieves the best reported scores on all four background metrics and both CLIP metrics. For the nine named categories, we varied only the switch step and reused the spatial and bitwise thresholds. Tuning these thresholds for real images may further improve the balance between edit strength and preservation.
[1] Hu et al. Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing. ICCV 2025, Sections 3 and 4.1.
GRN was trained to generate images from text. This ability alone does not guarantee that GRN can make a localized edit to image. We ran this experiment to test whether switching prompts midway through refinement is enough to edit a source image while preserving content outside the requested region. In Paper Section 5.3, we compare direct branching, which lets every bit follow the editing prompt, with RefineEdit, which updates selected bits and anchors the rest to the source trajectory. Both use the same GRN and, for each image, the same source state, switch step, and number of remaining steps. We used the Original settings and evaluated on images held out during parameter selection (Appendix B.2).
Direct branching follows the editing prompt well (edited CLIP 23.76), but it also changes details outside the target region. Across the evaluation set, routing raises background PSNR by 10.01 dB and lowers background LPIPS from 0.1162 to 0.0318, with a 0.32 decrease in edited CLIP. With the backbone and source state held fixed, this gain in background fidelity shows that selective routing confines edits more reliably than a prompt switch alone. Appendix C shows that the same strategy also works with a source reference constructed from a real image.