- Rating
- 4
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This work introduces REFFLOW, a training-free framework for image editing based on residual instance transport. Built upon a frozen flow-based text-to-image (T2I) model, REFFLOW designs a reference-induced velocity residual module and a Relationally Consistent Reference Value Transport mechanism. By optimizing intra-image feature correspondences and performing spatially gated residual correction, it achieves high-fidelity reference-guided editing without inversion or fine-tuning. The framework natively supports complex tasks such as multi-reference composition, typography editing, and texture transfer.
Critical strengths
- This work identifies drawbacks in two major branches of training-free editing methods: conventional text-guided approaches fail to perform instance-level fine-grained editing, while existing reference-guided methods merely conduct naive attention feature replacement without optimizing cross-image correspondences, which leads to structural inconsistency and degraded fidelity.
- This work proposes the reference-induced velocity residual to enable lightweight, controllable reference appearance correction while preserving the original text-guided semantic editing trajectory and keeping the backbone model fully frozen.
- This work designs the Relationally Consistent Reference Value Transport mechanism to overcome the limitations of conventional independent token-wise matching. It optimizes cross-image correspondences under intra-image feature relational constraints and mitigates detail artifacts caused by structural misalignment.
- This work for the first time realizes training-free multi-reference image editing using a completely frozen flow-based T2I model, extending the scope to complex editing scenarios including typography editing and texture transfer.
Critical weaknesses
- RefEdit‑Eval is a self‑curated benchmark. The paper only presents aggregated overall results without per‑task score for typography editing, texture transfer, object editing and style transfer. Per‑category metrics would help readers better understand where REFFLOW excels and where it still has shortcomings.
- The paper lacks quantitative experiments targeting multi‑reference scenarios.
- While failure cases are briefly discussed in Appendix I, the analysis remains qualitative. Adding quantitative statistics for different failure categories would enrich the discussion of the method’s limitations.
Questions for authors
- RefEdit‑Eval is a self‑curated benchmark. In the paper, only aggregated overall results are reported, without separate per-task scores for typography editing, texture transfer, object editing, and style transfer. Could you please provide per-category metrics to help readers better understand the strengths and remaining limitations of REFFLOW across these individual tasks?
- The current work does not include quantitative experiments under multi-reference scenarios. Are there any quantitative results compared to other methods?
- Although failure cases are briefly discussed qualitatively in Appendix I, no quantitative statistics are provided for distinct failure categories. Could you add quantitative statistics for different failure types to further support and enrich the discussion on the limitations of your method?
5 comments
Response to W2/Q2: Quantitative Multi-Reference Evaluation
We thank the reviewer for highlighting the need for quantitative multi-reference evaluation. To address this concern, we have conducted additional quantitative experiments covering two to five reference images, comparing RefFlow against two representative multi-reference editing models, DreamOmni2 and Qwen-Image-Edit-2511, on the same editing cases.
The new results are reported in Table 2 (p. 9), covering reference fidelity (CLIP-FG and DINO-FG), text alignment (CLIP-T), background preservation (PSNR-BG and LPIPS-BG), and editing success (Human-SR). RefFlow consistently achieves better aggregate performance than both baselines across these metrics, demonstrating its effectiveness in multi-reference editing while preserving unrelated source content.
Table 2: Quantitative comparisons on multi-reference editing. Results are averaged across editing cases with two to five reference images. The best and second-best results are bolded and underlined, respectively. (p. 9 of the updated manuscript.)
| Method | CLIP-FG ↑ | DINO-FG ↑ | CLIP-T ↑ | PSNR-BG ↑ (dB) | LPIPS-BG ↓ | Human-SR ↑ (%) |
|---|---|---|---|---|---|---|
| DreamOmni2 | 0.719 | 0.134 | 16.7 | |||
| Qwen-Image-Edit-2511 | 0.309 | 14.13 | 0.343 | |||
| RefFlow (Ours) | 0.907 | 0.803 | 0.369 | 26.70 | 0.065 | 86.7 |
Additional side-by-side qualitative comparisons are provided in Figure 11 (p. 19).
Response to W3/Q3: Quantitative Failure Analysis
We thank the reviewer for this constructive suggestion. Building upon the qualitative failure analysis in the original submission, we have added a quantitative breakdown of failure categories in Appendix J (Table 7, p. 24).
Table 7: Failure statistics of RefFlow. Frequency of different failure types across 40 unsuccessful editing cases. Multiple labels may be assigned to each case. (Appendix J, p. 24 of the updated manuscript.)
| Failure category | Count | Incidence (%) |
|---|---|---|
| Edit Omission | 7 | 17.5 |
| Reference Appearance Mismatch | 22 | 55.0 |
| Prompt Following Failure | 9 | 22.5 |
| Source Preservation Failure | 12 | 30.0 |
| Rendering Artifacts | 11 | 27.5 |
Specifically, we analyze 40 unsuccessful editing cases identified through human evaluation and classify them into five failure categories: Edit Omission (17.5%), Reference Appearance Mismatch (55.0%), Prompt Following Failure (22.5%), Source Preservation Failure (30.0%), and Rendering Artifacts (27.5%). Since a single editing result may exhibit multiple failure types, we adopt multi-label annotation.
The analysis shows that reference appearance mismatch is the most frequent failure type, indicating that preserving fine-grained instance-specific details remains a primary challenge. Together with the qualitative example in Figure 16 (p. 24), these additional statistics provide a more systematic characterization of RefFlow's remaining limitations.
We sincerely thank the reviewer for their positive assessment of our work and constructive feedback. We appreciate their recognition of RefFlow's contributions, and believe that the additional task-wise evaluations, multi-reference comparisons, and quantitative failure analysis have further strengthened the experimental evidence and clarified the strengths and limitations of our approach.
Response to W1/Q1: Task-wise Quantitative Evaluation
We thank the reviewer for this constructive suggestion. To provide a more fine-grained assessment beyond the aggregated results, we have added a task-wise quantitative evaluation on RefEdit-Eval in the updated manuscript.
Specifically, Appendix F (Table 4, p. 17) reports five evaluation metrics (CLIP-FG, DINO-FG, CLIP-T, PSNR-BG, and LPIPS-BG) separately across five editing categories: Object Placement, Object Replacement, Typography Editing, Texture Transfer, and Style Transfer, following the same evaluation settings as Table 1.
Table 4: Task-wise quantitative results on RefEdit-Eval. Performance of RefFlow across five editing categories. The best result in each metric is bolded. (Appendix F, p. 17 of the updated manuscript.)
The results reveal distinct performance characteristics across tasks. RefFlow achieves strong reference fidelity in typography editing and object placement/replacement, while object placement also exhibits favorable background preservation. Meanwhile, texture transfer shows relatively lower DINO-FG, and style transfer exhibits higher LPIPS-BG, highlighting task-dependent challenges in reference fidelity and source preservation.
These additional results provide a more detailed assessment of RefFlow's strengths and remaining limitations across different editing categories.