- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper tackles the problem of object removal in panoramic videos. Previous approaches for video object removal have focused on perspective videos. Hence a new simulated training data, approach and evaluation dataset is proposed. There qualitative examples in demo page shows the effectiveness of their approach.
Critical strengths
- Novel problem. Object removal approaches have mostly looked into perspective videos. The paper extends it to previously underexplored 360° videos.
- New Dataset. New Training and evaluation dataset has been created to tackle this novel approach.
- The qualitative examples show practically better removal compared to baselines.
Critical weaknesses
-
Limited object-removal evaluation: Since GT videos are not available for PanoVOR-Wild, along with the VLLM metrics, the authors should also consider reference-free object removal metrics TokSim [1] and ReMOVE [2].
-
Performance across different effects: Can the authors breakdown performance across different effect categories (e.g., shadows, reflections etc.)?
-
Limited Baselines: Since SVOR and VACE are closely related to the proposed model's initialization. They are more like ablations. The authors should compare with additional (perspective) video object-removal metrics like ROSE, Minimax-remover, Object-Wiper, Omnimatte-zero etc.
-
Contribution of pretrained models and training data: The proposed approach builds upon pretrained VACE and SVOR models, which already benefit from extensive training. Can author add a discussion or quantify how their method improves on this.
[1] Object-WIPER: Training-Free Object and Associated Effect Removal in Videos, CVPR 2026 [2] ReMOVE: A Reference-free Metric for Object Erasure, CVPRW 2024
Questions for authors
Please refer the weakness section.