- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
- The paper combines precise layered synthetic edits, multi-task mosaicking, and subsequent visual-coherence refinement. LoRA adaptation improves scribble-guided editing on VIBE, with additional results on a second backbone.
Critical strengths
- The distractor-scribble control usefully distinguishes exposure to multiple marks from supervision for multiple requested edits.
- Large improvements over the base model are supported by component ablations, a second backbone, and a small human study.
Critical weaknesses
- The experiments demonstrate useful data sources, but do not isolate the benefit of their proposed training order from simply adding more data and training.
- Equal numbers of training examples need not imply equal supervision: mosaicked examples contain more source images and requested edits.
Questions for authors
- Evidence request: Is there a comparison with mixed or reversed-order training using the same data exposure and training budget? This would establish whether the curriculum order itself matters.
- Clarification: In the supervision comparisons, how were source-image exposure, supervised edit counts, and training compute controlled across single-task and mosaicked examples?
3 comments
Solved my concerns, so I will keep my rating.
Thank you for confirming that our responses addressed your concerns and for supporting our work. We will incorporate the additional experiments and clarifications from the rebuttal into the revision.
Title: Response to Reviewer 68Cf (1/1)
W1 & Q1: Effect of the training order
Thank you for this suggestion. We agree that the original experiments did not isolate the benefit of stage ordering from that of additional data and training. We have therefore added two complementary controls. All configurations use the same datasets, a total of 4,500 training steps, and a global batch size of 64.
Reversing the stages reduces VC from 93.81 to 88.47, a 5.34-point difference, despite retaining the same per-source training-step allocations. This provides evidence that the stage order affects performance under the same data and training budget.
The mixed-training results provide complementary evidence: our schedule achieves 2.03 points higher VC than the strongest tested mixture (1:1), with similar IA (90.16 vs. 90.47). Overall, the proposed schedule achieves the highest VC among the tested configurations, with the clearest benefit in visual coherence, consistent with the purpose of Stage II.
W2 & Q2: Supervision exposure in the Sec. 3.2 comparison
Thank you for pointing this out. We agree that equal numbers of training examples do not imply equal amounts of supervision. In Sec. 3.2 (Figure 3), “equal-size” refers to 180K training examples per dataset. All three settings use 4,000 optimization steps and a global batch size of 64, corresponding to 256K training-example presentations:
Under this sampling mixture, the single-task and distractor-scribble settings each receive 256K source-image exposures and 256K supervised-edit exposures, while the multi-task setting receives approximately 358.4K of each. These counts include repeated presentations and should not be interpreted as numbers of distinct source images.
The original comparison therefore evaluates different supervision formats under matched training-example and optimization-step budgets, but does not match cumulative edit exposure. To address this difference, we additionally extend single-task training to 6,000 steps. This increases its cumulative edit exposure to 384K, exceeding that of the multi-task setting:
Longer single-task training improves 3-Task performance by 7.20 points, confirming that additional training does help. Nevertheless, the multi-task setting remains 9.89 points higher on 2-Task and 12.85 points higher on 3-Task, despite using fewer optimization steps and fewer cumulative edit exposures. This multi-task advantage comes with a lower 1-Task score in this comparison (85.09 vs. 87.47).
Thus, increasing single-task exposure and training steps alone does not reproduce the observed multi-task gains. These results support the value of training on jointly specified scribbles, instructions, and edit targets, beyond simply increasing the cumulative number of supervised edits.