- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes RolloutRemover, a scribble-guided object removal method built on Wan2.1-T2V-1.3B with LoRA fine-tuning. Image removal is cast as generating a 14-frame latent sequence: a scribble-intent frame, a predicted removal-region mask (f2), the source frame, a 10-frame latent "rollout", and the object-removed target. The rollout is built analytically in latent space. Corruption frames interpolate from the source latent to a noise anchor, in which the removal region is replaced by Gaussian noise; restoration frames then interpolate from the anchor to the target (Sec. 3.2, Eqs. 3–8). The model is trained with flow matching on about 50K pairs from OBER and CORNE. The authors also introduce SGORBench: 300 samples, each with a procedurally generated scribble, an object mask and an object-effect mask.
Critical strengths
- Practical problem: users give rough scribbles, and the model jointly infers the removal region and result.
- Ablations of rollout order, and endpoint-only prediction show that ordered intermediate supervision helps.
Critical weaknesses
- Scribble comparison is unfair: test scribbles share the training generator, while baselines simply use scribbles as masks.
- With dense masks it trails OSOR and OmniPaint (Table 2), so the rollout's added benefit is unsupported.
- , and are ablated on the 300-sample test set, in single runs without variance.
- The Wan2.1-T2V-1.3B backbone choice is unjustified, and training steps or epochs are never reported.
Questions for authors
- How exactly were the SAM 2.1 masks in Table 10 produced (prompt type, number of points, mask selection, dilation)? What is their IoU against the ground-truth masks? Why do all baselines do worse with SAM masks than with the raw scribble?
- Were , and selected on the SGORBench test set? Can you report the ablations on a held-out split with multiple seeds and confidence intervals?
- Why was Wan2.1-T2V-1.3B chosen over other video backbones (e.g., CogVideoX, HunyuanVideo) or an image backbone such as FLUX? How many training steps or epochs were used?