- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper addresses long-horizon style inconsistency in open-ended streaming video stylization. Existing diffusion-based methods generate locally smooth frames but produce mismatched styles when objects or scenes reappear after leaving the active context, leading to cumulative global style drift. The authors propose EverStyle with three core modules: SISM stores and retrieves stylization residuals for recurring content; RSCR trains the generator to reproduce past stylization under different temporal contexts; EA-SDM aligns outputs to the initial style distribution to reduce global drift. Experiments show EverStyle preserves stylization quality and improves long-horizon consistency for revisited scenes and recurring content. Ablation studies verify the effectiveness of each main module.
Critical strengths
- This work targets a practical problem unique to open-ended streaming stylization. When content disappears from the active context and later reappears, its stylized appearance often changes. Existing temporal consistency methods mainly reduce short-term flicker and overlook this long-horizon recurrence issue. The proposed memory and distribution anchoring designs target this open-ended streaming setting.
- The framework achieves strong qualitative and quantitative results against baselines while maintaining competitive stylization quality. Ablation studies confirm the individual contribution of SISM, RSCR and EA-SDM. Tests on sequences over 130k frames demonstrate stable long-streaming operation.
Critical weaknesses
- The central claim of improved consistency for recurring objects and reduced global style drift over long sequences lacks dedicated quantitative experiments. Visual results offer partial evidence, but there are no tailored metrics or controlled tests to measure appearance mismatch of reappeared content or the speed of cumulative drift.
- The paper has no failure case visualization or analysis. The performance boundary of EverStyle remains unclear, such as cases with residual style drift or failed SISM retrieval.
- The presentation leans too heavily on technical details, making the motivation less intuitive. The method section would benefit from a high-level technical overview. In addition, the overview figure Fig.2 appears cluttered and hard to follow. Excessive fine-grained details obscure the main pipeline and weaken readability.
Questions for authors
- Could you add dedicated quantitative metrics to measure appearance mismatch for recurring objects and the rate of cumulative global style drift, to validate your core claim about long-horizon consistency?
- What are EverStyle’s primary failure modes? Please describe scenarios where SISM retrieval fails or EA-SDM cannot fully stop long-horizon style drift, and explain their underlying causes?
- Could you add a high-level technical overview to clarify the core pipeline?
5 comments
Author Response (2/2)
Q4: Validation about long-horizon consistency.
A4: Thank you for this valuable suggestion. Following your recommendation, we added dedicated quantitative metrics for both aspects on IVEBench-Cycle: (1) the appearance mismatch of reappearing content and (2) the cumulative global style drift over time. In short, EverStyle has the lowest mismatch among all five methods, and its style similarity shows no decline over time (a net change of ).
-
Appearance mismatch of reappearing content. IVEBench-Cycle repeats source videos, so identical content reappears at known frame positions. We compare corresponding frames from the first and final complete cycles using LPIPS/DINO and Contrastive Style Descriptors (CSD), a metric specifically designed for image style similarity (Somepalli et al., Measuring Style Similarity in Diffusion Models, ECCV 2024). The results are as follows:
Method LPIPS DINO Matched-frame CSD StreamV2V 0.0447 0.9762 0.9665 SANA-Streaming 0.4292 0.7299 0.7138 LiveEdit 0.1444 0.9013 0.9184 JoyAI-Video-Edit 0.0857 0.9649 0.8943 EverStyle 0.0436 0.9778 0.9802 From these results, we observe that EverStyle achieves the best scores on all three metrics, supporting consistent reproduction of the earlier stylized appearance.
-
Cumulative global style drift. We use the first complete cycle as a fixed reference and track the cross-frame CSD at the 25%, 50%, 75%, and final-cycle positions, comparing temporally separated positions to reduce reliance on matching frame content. The results are as follows:
Method 25% CSD 50% CSD 75% CSD 100% CSD CSD (25% 100%) StreamV2V 0.7522 0.7512 0.7505 0.7491 SANA-Streaming 0.6795 0.6933 0.6810 0.6523 LiveEdit 0.8068 0.8088 0.8105 0.8069 JoyAI-Video-Edit 0.7939 0.7916 0.7947 0.7936 EverStyle 0.8727 0.8706 0.8713 0.8736 From these results, we observe that EverStyle maintains the highest CSD at every position, with a net change of only from the 25% position to the final cycle, i.e., its style similarity does not decline over time.
We have added these evaluations to Appx. B.3 (highlighted in blue). We hope these additional metrics can help resolve your doubt and strengthen the quantitative validation of our core claim about long-horizon consistency.
Q5: More discussions and explanations regarding failure modes.
A5: Thank you for raising this question. The primary failure modes are unreliable historical corrections and local drift despite a stable overall style. We describe the scenarios and their underlying causes below.
- Scenarios where SISM retrieval fails. Large viewpoint or appearance changes can weaken the source-feature correspondence, and eviction from the fixed-size bank can remove a useful historical residual. When no reliable match remains, confidence calibration suppresses the correction and generation falls back to the original sink-and-recent path. In addition, verification can accept an incorrect stylization shared by two observations, allowing the error to persist across revisits, as shown in Fig. 16a.
- Scenarios where EA-SDM cannot fully stop long-horizon style drift. EA-SDM constrains early and current frames jointly at the distribution level without pixel-wise correspondence. It can therefore preserve the overall style while fine brushstrokes or contours change, as in the oil-painting example in Fig. 16b.
We have added these failure cases and the corresponding discussion to Appx. B.11 (highlighted in blue). We hope these explanations can address your question and make the causes of the remaining failures clearer.
Q6: Adding high-level overview.
A6: Thank you for this suggestion. Following your recommendation, we have added a concise high-level overview and a simplified pipeline figure (Appx. A.1 and Fig. 9, highlighted in blue), and the caption of Fig. 2 now points to them. The overview states the two consistency requirements, i.e., recovering the earlier stylization of recurring content and maintaining the overall style as content changes, and how SISM, RSCR, and EA-SDM address them. The figure separates streaming generation from the training objectives and omits layer-level details, as a companion to Fig. 2. We hope this addition can make the core pipeline easier to follow.
Thanks for your comments, which helped us further improve the analysis and presentation
Dear Reviewer i22S,
Thank you again for your time and thoughtful comments during the review process. Inspired by your comments, the revised paper now includes more quantitative results on long-horizon consistency, an analysis of failure cases, and a high-level overview of the method. If you have any further questions, we are happy to discuss and address them.
Author Response (1/n)
A1: Thank you for highlighting the need for more direct quantitative evidence. We clarify that Sec. 4.2 (Table 1) already provides two controlled quantitative evaluations of recurring-content consistency. IVEBench-Cycle compares identical source frames across distant cycles, while CAM evaluates revisits selected using field-of-view overlap annotations. Both quantify the appearance mismatch using LPIPS/DINO.
Following your suggestion, we further add a dedicated style metric, Contrastive Style Descriptors (CSD), for matched-frame comparisons, and measure cumulative drift by tracking the cross-frame CSD at the 25%, 50%, 75%, and final cycle positions. EverStyle achieves the highest matched-frame CSD and maintains the highest cross-frame CSD at all four positions, with a net change of +0.0009 from the 25% position to the final cycle. A4 provides the protocols and full results.
We hope these additions can help resolve your doubt and strengthen the quantitative validation of recurring-content consistency and long-horizon style retention.
A2: Thank you for this important comment. Following your suggestion, we have added failure case visualizations and the corresponding analysis to Appx. B.11 and Fig. 16 (highlighted in blue).
For residual style drift, Fig. 16b shows an oil-painting result whose broad palette and distant ridgeline remain stable, while fine brushstrokes and rock contours change between frames 773 and 5,923. For persistent errors, Fig. 16a shows a case where a dim interior is rendered as bright storefronts and the error persists across recurrences: since SISM verifies agreement between observations, an error shared by both can pass verification and be reused.
For failed SISM retrieval, the typical scenarios are large viewpoint or appearance changes and the eviction of a useful entry. When no reliable correspondence remains, confidence calibration suppresses the correction and generation falls back to the original attention path.
These cases clarify the performance boundary: EverStyle works best when recurring content keeps a reliable source correspondence under a fixed target style. A5 further explains the underlying causes. We hope these examples and clarifications can address your concern.
A3: Thank you for this helpful suggestion. Following your recommendation, we have added a high-level technical overview and a simplified pipeline figure to make the motivation and the main pipeline easier to follow (highlighted in blue). Due to the page limit, they are placed in Appx. A.1 and referenced from the caption of Fig. 2.
The overview explains the two requirements behind our design: recovering the established appearance of recurring content and maintaining the overall style as content changes. The accompanying Fig. 9 shows one source chunk passing through the streaming generator, with SISM represented as a single side branch in panel (a), and RSCR and EA-SDM as training objectives in panel (b). Layer-level details remain in Fig. 2 and Appx. A.2.
We hope these additions can make the motivation and the core pipeline of our method clearer.