- Rating
- 4
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes WorldRoPE, a probabilistic world-centric rotary positional encoding for multi-view attention. It represents each image token using a mixture of volumetric Gaussian primitives to capture multiple depth hypotheses, depth uncertainty, and patch extent. By deriving a closed-form expectation of the rotary operator over the projected Gaussian distributions, WorldRoPE incorporates probabilistic 3D geometry into cross-view attention. Experiments across multiple tasks and architectures demonstrate its effectiveness.
Critical strengths
- Elegant and principled formulation. The paper presents an elegant mathematical derivation that provides a solid theoretical foundation for the proposed design. The resulting method is well motivated and interpretable.
- Strong empirical results. WorldRoPE achieves consistent improvements across multiple architectures, tasks, and benchmarks, demonstrating its practical effectiveness and broad applicability.
- Meaningful learned geometry. The visualizations in Figures 7, 10, and 11 suggest that WorldRoPE can learn plausible 3D scene structures without explicit depth supervision, providing further qualitative support for the proposed geometric modeling.
Critical weaknesses
- Computational overhead. Projecting Gaussian primitives across views introduces additional geometric computation, which is an important factor for application. The efficiency analysis in Figure 13 deserves a place in the main paper, and exact runtime measurements should be reported rather than only plots.
- Potential information loss from hypothesis aggregation. WorldRoPE combines multiple Gaussian hypotheses into a single expected rotary operator per frequency block. However, distinct multimodal distributions may produce identical expected rotations, potentially discarding geometric information relevant to cross-view matching. It would be interesting to compare the current approach with an alternative that computes attention distributions separately for each Gaussian hypothesis and aggregates them after softmax. Such a comparison could help assess whether the current aggregation strategy loses useful information.
Questions for authors
See weaknesses
3 comments
Dear Reviewer Z1Lw,
Thank you again for your insightful review and constructive comments. Following your suggestions, we added runtime and memory comparisons to the main paper and compared our aggregation with your suggested alternative. Your feedback helped us provide stronger evidence of WorldRoPE's practicality and demonstrate that its default design offers an effective accuracy–cost tradeoff.
We truly appreciate your positive assessment of our work. Please let us know if anything else is unclear; we would be happy to clarify further.
Note: We have also uploaded an interactive 3D viewer as supplementary material, allowing you to explore the Gaussian primitives predicted at each attention layer. Please open the
3d_viewer.htmlfile in Supplementary Material to use it.
Best regards,
Authors
Dear Reviewer Z1Lw,
Follow-up on [W2]: Additional ablation on Objaverse
To check whether the result in our original response holds beyond RE10K, we additionally ran the same ablation on Objaverse. The table below compares three WorldRoPE variants that differ only in hypothesis aggregation: one suggested by the reviewer and two additional variants we explored (see Appendix A.13 for the detailed equations). We set M = 4 in this comparison. We hope these results further address your question.
RE10K Objaverse Method # of rotated key tokens PSNR ↑ SSIM ↑ LPIPS ↓ PSNR ↑ SSIM ↑ LPIPS ↓ WorldRoPE (default) ×1 26.75 0.846 0.073 22.52 0.896 0.113 WorldRoPE with mixture of softmax (reviewer suggested) ×M 26.76 0.845 0.073 22.52 0.895 0.113 WorldRoPE with score scaling (additional variant) ×M 26.62 0.843 0.074 22.31 0.893 0.117 WorldRoPE with prior weighting (additional variant) ×M 26.72 0.845 0.073 22.62 0.897 0.110
- WorldRoPE with reviewer's suggested mixture of softmax again performs on par with the default, whereas WorldRoPE with score scaling degrades all metrics. Interestingly, WorldRoPE with prior weighting further improves all three metrics on Objaverse (+0.10 dB PSNR, +0.001 SSIM, −0.003 LPIPS vs. the default), although, like the other variants, it requires four times as many rotated key tokens. (M=4)
- Notably, all four variants still outperform RayRoPE and URoPE on both datasets, suggesting that WorldRoPE's improvement is robust to the choice of aggregation rule.
- These results further support the default aggregation as an effective accuracy–cost tradeoff: comparable performance using only of the rotated key tokens.
Additional remark
We sincerely appreciate your comments, which have been very helpful in improving our work. If there are any other questions or areas where you would like more information, please feel free to reach out, and we will gladly provide further details.
Best regards,
Authors
Response to reviewer Z1Lw
Thank you for your thoughtful and thorough review of our work.
[W1] “Computational overhead”
[W2] “Potential information loss from hypothesis aggregation”
We sincerely look forward to engaging in further discussions.