- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper presents ProgressNet, a training-free framework for progressive sketch-conditioned image generation. It supports stroke addition, erasure, and prompt updates using frozen FLUX.1-schnell and Union ControlNet. The method combines previous-output image conditioning (PCM), selective reuse of previous-turn attention keys and values (LS-KVI), and adaptive memory-strength modulation (BAC). The authors evaluate generation quality and progressive consistency on several sketch datasets. They also provide qualitative examples, ablations, and user studies.
Critical strengths
-
The paper addresses a useful interactive generation problem. Supporting additions, erasures, and prompt changes while preserving established content could improve sketch-based creative workflows.
-
The framework requires no additional training and introduces little inference overhead. The reported latency of 0.829 seconds per turn is promising for interaction. The experiments also show substantial improvements over the FLUX+ControlNet baseline.
Critical weaknesses
-
The quantitative evaluation does not sufficiently measure local editing effectiveness. Most metrics assess whole-image similarity, text alignment, or distributional quality. PFC combines inter-turn similarity with FID, but neither component directly checks whether the requested edit was performed. A simple counterexample is to generate an image from the initial sketch and prompt, then return it unchanged in every subsequent turn. This would achieve perfect inter-turn similarity and could retain a good FID despite ignoring all edits. The user study does evaluate editing, but important details are missing, including participant counts, numbers of judgments, and how responses were converted into the normalized scores. These limitations make it difficult to assess the claimed balance between content preservation and editing responsiveness.
-
The additional benefit of LS-KVI and BAC over PCM alone is not sufficiently established. PCM is a straightforward way to introduce memory by conditioning on the previous output. It already accounts for most of the quantitative improvement. In Table 4, at full completion, PCM alone achieves a better FID-I than the full method (36.6 versus 37.3), with comparable DINOv2 similarity. The full method improves FID-C and text-alignment scores a bit, but the ablation does not directly evaluate its claimed advantages in progressive consistency and editing. The user studies also exclude ablation variants. A focused human comparison between PCM alone and the full method would help establish whether the additional components provide a meaningful benefit.
-
The Sketch-a-Sketch baseline is inconsistently identified. Section 5.1 names Sketch-a-Sketch, but the cited Sarukkai et al. (2024) reference is titled “Block and Detail: Scaffolding Sketch-to-Image Generation.” These are distinct projects. This leaves the evaluated implementation and configuration unclear.
Questions for authors
-
Can authors provide more details about the user studies, including participant counts, evaluation criteria, and the exact normalization procedure used for Table 3?
-
Can authors directly compare PCM alone with the full method on editing success and preservation of unedited content? A focused user study on the existing editing examples would be particularly helpful.
-
Which implementation was used for the S-a-S baseline?
7 comments
Table R4. Layer choice for K/V injection, six layers each (random: mean ± SD over three draws).
| Metric | Non-vital (Ours) | Vital | Random (mean ± SD) |
|---|---|---|---|
| Stroke adherence ↑ | 0.0982 | 0.0719 | 0.0763 ± 0.0040 |
| Unedited LPIPS ↓ | 0.1243 | 0.1508 | 0.1527 ± 0.0026 |
| Color drift ↓ | 14.27 | 22.75 | 21.45 ± 2.15 |
Notably, vital or random layers are worse than no injection at all. LS-KVI builds on StableFlow but with different philosophy of injecting at the opposite end (L505–517 updated). BAC keeps sketch edges from bleeding in (Fig. 9) and recovers the FID-C cost of LS-KVI in Table 4 (0.162 → 0.143). On add → erase sequences (updated Table 8), all five metrics improve monotonically from PCM-only to PCM + LS-KVI to the full system.
Question 3 · Weakness 3
Weakness 3: “The Sketch-a-Sketch baseline is inconsistently identified. …”
Question 3: “Which implementation was used for the S-a-S baseline?”
Good observation. We used the publicly released Sketch-a-Sketch ControlNet checkpoint (vsanimator/sketch-a-sketch), and we have now fixed the citation in Section 5.1 (L319), Table 6 and Appendix D.
Weakness 1 (PFC and local editing)
Weakness 1: “… neither component directly checks whether the requested edit was performed. A simple counterexample is to … return it unchanged in every subsequent turn. …”
Thanks for highlighting this concern. We agree with the reviewer on both points. This is now limitation (ii) in Section 6, and we have revised the introduction (L125–127) from “frame-to-frame similarity alone rewards a method that ignores the new stroke” to “… ignores image quality”. We also test the reviewer’s counterexample, the baseline’s first-turn image repeated at every turn (Table Reb. 1(a)).
Table R2. Edit-following metrics on 100 FS-COCO sequences, including the frozen output.
| Method | Stroke adherence ↑ | Unedited LPIPS ↓ | Color drift ↓ |
|---|---|---|---|
| Frozen first turn (Flux at 10%) | 0.000 | 0.000 | 0.00 |
| Flux+ControlNet | 0.105 | 0.192 | 22.0 |
| StableFlow | 0.060 | 0.110 | 27.0 |
| Ours | 0.0982 | 0.1243 | 14.27 |
With the output frozen, everything stays at zero. Especially, every compared method follows the strokes (0.105 / 0.060 / 0.0982), so Table 2 compares methods that respond to the edits. ProgressNet keeps 94% of FLUX+ControlNet’s adherence with 35% less change in the unedited regions and the lowest color drift, whereas StableFlow attains locking (lowest unedited LPIPS, highest color drift; Figs. 7–8, 13–35).
PFC was deliberately designed as a quality-adjusted temporal consistency metric (Appendix A.2, L858–859). Its motivation was empirical: frame-to-frame DINOv2 and LPIPS reward StableFlow more and more as it locks, while its FID-I collapses and ProgressNet’s stays flat (Table R1).
Table R1. PFC reconstructed from its underlying measurements on FS-COCO (StableFlow / Ours).
| Metric (StableFlow / Ours) | 10→20% | 30→50% | 80→100% |
|---|---|---|---|
| FID-I ↓ | 36.8 / 36.5 | 40.7 / 36.0 | 52.8 / 37.3 |
| DINO ↑ | .809 / .819 | .863 / .840 | .888 / .874 |
| LPIPS ↓ | .250 / .251 | .142 / .231 | .097 / .206 |
| PFC-DINO ↑ | 2.198 / 2.244 | 2.120 / 2.333 | 1.682 / 2.343 |
| PFC-LPIPS ↑ | 2.174 / 2.190 | 2.151 / 2.257 | 1.726 / 2.223 |
In Table 1, our DINOv2 rises from 0.400 to 0.413, whereas StableFlow’s falls from 0.397 to 0.359, and our FID-I ends at 37.3 against the baseline’s 67.9. Therefore, consistency counts only when quality is kept; we have now added this discussion to the appendix.
Finally, we think the reviewer has suggested meaningful studies about the paper: the user study of full ProgressNet vs. PCM-only (Table Reb. 1(c), Question 2). We are grateful for it. Together with parts (a) and (b), it now forms a new main-paper table, Table Reb. 1 (page 8), which Sections 5.1, 5.4 and 6 report from.
Following up - Reviewer zVtb
Dear Reviewer zVtb,
Thank you for your suggestions. We have tried to address your concerns, and we look forward to your further input and engagement during the rebuttal period.
We thank the reviewer for recognizing the usefulness of our work in the sketch domain, as well as its little computational overhead and clear improvements over the baseline. We address your questions below.
Question 1 · Weakness 1 (user study details)
Thank you very much for asking this question. We agree that these details of Table 3 (Section 5.3) were missing; they are now in Appendix D (Tables R6–R9), summarized below.
Participant counts: The user study has 49 participants across two evaluations; 25 fully answered the video-based one. They were recruited from open communities via an online Gradio interface (Appendix D, L1294–1295); both studies were double-blind, in randomized order.
Table R6. Demographics of the 49 participants (students: university).
Table R7. Study 1 (overall); all 49 completed it.
Table R8. Study 2 (operation-based), pairwise to focus on editing; all 49 completed it.
Table R9. Study 2 (video-based): 2 videos for each of the 6 methods (12 in total), 4 sliders each; 25 of 49 completed it.
Normalization procedure. Within each criterion, we sum each method’s score over participants and examples:
Normalized score = ( method’s total / total of all six methods ) × 100
The score is: Pref., times placed first; Coher. and the four video criteria, the slider value; Qual., the Likert rating coded [0–4]; Erase and Edit, pairwise comparisons won.
Since ProgressNet appears in every pairwise comparison and each baseline in one fifth of them, we also give its head-to-head win rates against S-a-S / SDXS / CB / Flux / StableFlow: Erase 93 / 91 / 90 / 86 / 66%, Edit 90.5 / 88.4 / 79.6 / 73.5 / 55.8%. StableFlow is the closest competitor, especially on Edit (55.8%), as now clarified in Section 5.3 (L425–429).
Question 2 · Weakness 2 (PCM alone vs. the full method)
Thank you very much for this suggestion. We now report the focused user study (20 participants, three examples per operation) in the main paper.
Table Reb. 1(c). PCM-only vs. the full system: % of judgments preferring the full system (counts).
Overall 95% Wilson intervals: [64, 77] (editing success) and [60, 74] (content preservation). We also run the same comparison on editing metrics over 100 FS-COCO sequences.
Table R3. Component ablation on the editing metrics.
Stroke adherence is the increase in Canny-edge recall of the new strokes between stages; unedited LPIPS and color drift (ΔE00) measure the change in the regions without new strokes. We observe a trade-off here: the full ProgressNet gives up about 3% of stroke adherence against PCM-only but attains 10% better unedited LPIPS and 13% less color drift. Moreover, the layer choice is what makes LS-KVI work.