- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper focuses on entropy context modeling in progressive 3DGS compression and proposes RACE. The paper points out that existing methods typically reuse static spatial priors across layers, so newly activated anchors lack cross-layer information, and the context granularity is also difficult to match the per-layer Gaussian distributions. Mechanisms such as generating a hint map from the attributes of Gaussians decoded in the previous layer and updating a shared triplane prior improve task performance, and this is validated on multiple datasets.
Critical strengths
The paper's problem motivation is supported by data. The number of new anchors is small, and refined anchors account for most of the payload, so updating the shared prior is a targeted design. The method preserves causality, the granularity index precedes attribute transmission, the decoder does not need to perform repeated searches, and the decoding overhead is close to that of PCGS. Experiments show that the method achieves improvements on multiple datasets.
Critical weaknesses
-
The paper lacks an asymptotic decoding comparison with PCGS.
-
Current 3DGS compression methods generally require per-scene optimization except for the FCGS family, so does the encoding time include training time? It is recommended to report the relevant metrics, because encoding time that excludes training time lacks practical significance for this type of problem.
Questions for authors
Answer the questions raised by the critical weakness.
Response to Reviewer Uw2z
Response to Reviewer Uw2z
We thank the reviewer for requesting a clearer account of decoding complexity and end-to-end optimization cost. We have added both theoretical and empirical measurements.
W1: Asymptotic decoding comparison with PCGS
Answer. We have added both measured decoding time and asymptotic analysis; RACE and PCGS have nearly identical decoding time and the same O(Ns) decoding order.
Table 3 now reports an average decoding time of 27.8 s for RACE and 27.4 s for PCGS over the same 19 scenes, corresponding to only a 1.5% increase. This small difference follows from the decoder design. Let Ns be the number of active anchors, K the fixed neighborhood size, and P=3 the directional planes. Hint splatting, neighborhood attention, and probability prediction cost O(PNs), O(KNs), and O(Ns), respectively. Since P and K are constants, RACE retains the O(Ns) decoding order of PCGS and only adds a linear context-construction term. The candidate-granularity search is encoder-only; the decoder reads the selected tuple directly and therefore has no ∣Ss∣ search factor.
Revision. Section 4.4, Table 3 and the new paragraph “Decoder complexity” (p. 10).
W2: Does encoding time include training?
Answer. No; the reported encoding time measures post-training bitstream coding and excludes per-scene optimization.
We now state this explicitly in the text and Table 3 caption. We additionally report matched optimization measurements on five scenes: PCGS versus RACE averages are 66.4 versus 122.6 minutes for training and 11.17 versus 23.25 GiB for peak GPU memory. Presenting these values separately prevents Table 3 from being interpreted as end-to-end training cost.
Revision. Section 4.4, revised Table 3 caption and the new matched training-cost table (p. 10).