- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The authors introduce the task of Infinite Video Editing, which aims to generate future video segments according to editing instructions while maintaining temporal continuity with the preceding content. To address this task, the authors propose InfinityEdit, a lightweight editing adapter built on a frozen Helios backbone. During inference, the adapter is activated only for the first chunk of each editing round, while subsequent chunks are generated by the frozen backbone. Experimental results demonstrate promising improvements in edit faithfulness and temporal consistency.
Critical strengths
-
The paper introduces a novel task that extends conventional in-place video editing to continuous editing of future video content.
-
The proposed Edit-Ignition strategy leverages the long-video generation capabilities of a pretrained backbone without requiring full-model fine-tuning.
Critical weaknesses
-
Limited Baseline Comparison: The current Helios-Base baseline relies solely on direct prompt replacement, which may fail to effectively capture scene-dependent relative editing instructions. I suggest that the authors include a stronger baseline that employs scene-aware prompt rewriting under the same backbone, history conditioning, and inference settings to better demonstrate the contribution of the proposed editing adapter.
-
Missing Ablation Studies: The paper lacks ablation studies on several key design choices, including the three attention modules, history corruption, the two-stage training strategy, and anchor resetting. Specifically, the authors should compare two settings: enabling the adapter only for the first text block versus keeping the adapter active throughout the entire editing stage. Such a comparison would help validate the advantages of this core inference strategy in terms of both editing quality and computational efficiency.
-
Limited Evaluation of Long-Term Editing: Although the paper focuses on infinite video editing, its main quantitative evaluation only considers three consecutive editing rounds. How does the proposed method perform when the number of editing rounds increases significantly (e.g., 10–20 rounds)? I am concerned that long-term editing may lead to error accumulation and forgetting of previously edited attributes.
Questions for authors
Can the proposed method maintain stable performance when handling conflicting or compositional editing instructions?
7 comments
Response to Reviewer bNFU (2/2)
[R2-2]
- Ignition policy and inference cost. Each edit round contains four chunks. We compare one, two, and four ignition chunks using the same final checkpoint. Four ignition chunks keep the adapter active throughout the round.
| Ignition chunks per edit round | Edit faithfulness | Visual quality | Preservation | Coherence |
|---|---|---|---|---|
| 1 (default) | 3.860 | 3.790 | 3.920 | 3.930 |
| 2 | 3.882 | 3.713 | 3.750 | 3.835 |
| 4 (adapter throughout) | 3.753 | 3.583 | 3.125 | 3.275 |
Two ignition chunks slightly improve faithfulness over one (+0.022), while one chunk gives the highest visual quality, preservation, and coherence. Four ignition chunks keep the adapter active throughout the edit round but reduce generation quality and stability. This decline is consistent with the adapter's training objective. Our adapter is trained to establish a high-quality edit consistent with the preceding video, not to sustain long rollouts within the same edit round. After the first chunk, the backbone's stronger generation prior supports more reliable continuation from the edited history. We therefore use the adapter for one ignition chunk and the backbone for the remaining chunks.
Activating the adapter for fewer chunks also reduces inference cost. On 20 cases, we measure:
| Policy (four chunks per round) | Median inference time (s/sample) | Effective edit FPS |
|---|---|---|
| 1 ignition chunk | 324.69 | 1.22 |
| 4 ignition chunks | 825.35 | 0.48 |
The one-chunk policy takes less than half the median inference time and achieves a higher effective edit FPS. Together, these results support our default in both editing quality and efficiency.
[R3] Thank you for raising this concern. We have added ten-round editing videos to the supplementary folder "multiple_round_cases". These videos show that our method applies successive edits beyond the three rounds in the main evaluation. Each requested edit takes effect, and later rounds build on the edited content. We also include a matched Helios-Base video using the same source and edit instructions.
For quantitative comparison, we evaluate 30 IID videos over ten editing rounds with the same VLM protocol for both methods. Scores range from 1 to 5, with higher values indicating better performance.
| Metric | Ours | Helios-Base |
|---|---|---|
| Edit faithfulness, rounds 1–10 mean | 4.14 | 3.36 |
| Rolling three-round coherence, rounds 3–10 mean | 3.70 | 3.04 |
Our method remains effective through round 10 and outperforms Helios-Base on both metrics. Some fine details may indeed drift over a long sequence, but edit faithfulness does not collapse across the ten rounds.
[A1] We conducted additional experiments with conflicting and compositional edit instructions. Representative videos are included in the supplementary folders "conflict" and "compositional".
- Conflicting instructions. We write a single instruction that requests two mutually exclusive changes at the same time, such as moving the camera both up and down or changing the same person into both ladudu and simpsons comic styles. The resulting videos remain fluent, although the two requests cannot both be satisfied. Because no output can fulfill both demands, this experiment examines whether generation remains stable under a contradictory instruction.
- Compositional instructions. We write a single scene-specific instruction that combines a style change with a camera movement and requests both in the same edit round. The resulting videos show the requested style change alongside the camera movement. This indicates that the adapter can combine these edit types within one instruction.
Therefore, current experiments show our method's stable generation under conflicting instructions and effective joint editing under compositional instructions.
Looking Forward to Your Further Feedback
Dear Reviewer bNFU,
We would like to express our sincere thanks once again for your efforts in reviewing our paper. As there are only two days left for discussion, we would kindly inquire if you have any further suggestions or concerns. We believe that our previous responses have adequatetly addressed your concerns. Should you have any further questions, we would greatly appreciate the opportunity to address them promptly.
Best regards,
Authors
Response to Reviewer bNFU (1/2)
We would like to thank you for your careful review and constructive suggestions. Please see our point-by-point responses to all weaknesses (R) and questions (A) below.
[R1] We have added a comparison between our method and Helios-Base with scene-aware prompt rewriting. Following the practice of ChronoEdit, we use Qwen2.5-VL-7B-Instruct to rewrite each relative edit instruction into a scene-aware prompt for Helios-Base. Both Helios-Base variants use the same backbone, history conditioning, and inference settings. We evaluate both variants and our method on the same 200-video benchmark.
Scene-aware rewriting improves Helios-Base on all four metrics relative to the raw-instruction reference, but it remains below our method on every metric. This comparison isolates the adapter's contribution from the effect of stronger prompt wording. We have added it to the revised appendix.
[R2-1] Thank you for the detailed suggestion. We have added ablations of the adapter components, history corruption, the two-phase curriculum, anchor resetting, and the number of ignition chunks. We also compare inference cost when the adapter is active for one versus all four chunks in an edit round. All quality results below use the same 200-video benchmark and four VLM metrics as Table 2. Scores range from 1 to 5, with higher values indicating better performance. Given the limited rebuttal period, the variants that require retraining and their full-model control use the same 10,000-step budget for a fair comparison. We will update those results after full retraining.
The modules play distinct roles:
History corruption improves all four scores. It exposes the adapter to degraded histories during training, helping it handle imperfect frames from its own rollout.
Phase 2 improves all four VLM scores. This further supports the role of stage-two training in stabilizing frames far from the history anchor.
Disabling anchor resetting lowers all four scores, including preservation by 0.160 and coherence by 0.200. Resetting the anchor to the first edited frame gives subsequent chunks a reference aligned with the current edit. Without this update, the anchor remains tied to the original source and may pull later chunks back toward the pre-edit appearance. The score drops are consistent with anchor resetting's role in keeping the edited stream stable.