- Rating
- 4(+1)
- Confidence
- 4(+1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper proposes a framework for 3D semantic occupancy prediction, GaussianCollab. By transmitting tokenized representation, the proposed method achieved better overall results on the tested Semantic-OPV2V and Co3SOP.
Critical strengths
- The communication medium and the corresponding collaboration protocol are well motivated, yielding an overall better result.
- The SIC-guided selection further improves the method from a communication-efficiency perspective.
Critical weaknesses
The benefit of using latent queries over decoded attributes is not fully justified. From GSCollab-112 N/I/T results we can see a ~2 mIoU degradation to achieve 5.5 -> 0.9 CV reduction. From the VOGS-L results, N Protocol decoded attributes can achieve similar CV as T protocol latent queries. This raises the question of whether a GSCollab N using decoded attributes can achieve similar performance. Further design justification or an additional comparison on a controlled CV will help address this concern.
Questions for authors
Please see the weaknesses section.
7 comments
Official Comment 2 for Jsx7-Q1 — Is latent communication justified at controlled CV?
Question. “The benefit of using latent queries over decoded attributes is not fully justified. From GSCollab-112 N/I/T results we can see a ~2 mIoU degradation to achieve 5.5 -> 0.9 CV reduction. From the VOGS-L results, N Protocol decoded attributes can achieve similar CV as T protocol latent queries. This raises the question of whether a GSCollab N using decoded attributes can achieve similar performance. Further design justification or an additional comparison on a controlled CV will help address this concern.”
Response: We corrected communication-volume (CV) accounting for compressed GSCollab variants and reran validation. The updated main results appear in our separate official comment, “Corrected CV and updated main results.”
Additional experiments are underway to address your proposed comparison. We will present their accuracy and measured CV in one ablation table in a single shared follow-up official comment.
Official Comment 5: Consolidated controls for latent and attribute collaboration
These Semantic-OPV2V controls use 12,800 initial Gaussians, 0.4 m matching, and all 1,980 validation frames. N uses no SIC, I uses SIC at inference only, and T uses SIC in training and inference. CV (MiB per collaborative frame) counts the unfiltered response for N, or the packed request and selected response for I/T. IoU/mIoU are percentages.
| # | Backbone setting | Transmitted Content | Token Length | Fused Content | Stack | IoU | mIoU | CV |
|---|---|---|---|---|---|---|---|---|
| 0 | VOGS-L (N) | Shared Refinement Head Decoded Attributes | 7 pose + 17 attributes = 24 (96 B) | Shared Refinement Head Decoded Attributes | -- | 71.54 | 38.90 | 0.941 |
| 1 | GSC-112 (N) | Shared Refinement Head Decoded Attributes | 7 pose + 17 attributes = 24 (96 B) | Shared Refinement Head Decoded Attributes | ✓ | 73.22 | 41.90 | 0.976 |
| 2 | GSC-112 (I) | Pose + Latent Queries | 7 pose + 112 query = 119 (476 B) | Latent Queries | ✓ | 73.22 | 42.47 | 0.914 |
| 3 | GSC-112 (T) | Pose + Latent Queries | 7 pose + 112 query = 119 (476 B) | Latent Queries | ✓ | 72.47 | 42.03 | 0.773 |
| 4 | GSC-96 (T) | Shared Refinement Head Decoded Attributes | 7 pose + 17 attributes = 24 (96 B) | Shared Refinement Head Decoded Attributes | -- | 71.86 | 38.91 | 0.196 |
| 5 | GSC-96 (T) | Shared Refinement Head Decoded Attributes | 7 pose + 17 attributes = 24 (96 B) | Shared Refinement Head Decoded Attributes | ✓ | 73.29 | 41.19 | 0.206 |
| 6 | GSC-96 (T) | Pose + Latent Queries | 7 pose + 96 query = 103 (412 B) | Latent Queries | -- | 72.51 | 40.86 | 0.754 |
| 7 | GSC-96 (T) | Pose + Latent Queries | 7 pose + 96 query = 103 (412 B) | Latent Queries | ✓ | 72.87 | 42.64 | 0.695 |
| 8 | GSC-96 (T) | Pose + Latent Queries | 7 pose + 96 query = 103 (412 B) | Frame-Invariant Attr. Decoder Decoded Attributes | -- | 71.72 | 37.45 | 0.926 |
| 9 | GSC-96 (T) | Pose + Latent Queries | 7 pose + 96 query = 103 (412 B) | Frame-Invariant Attr. Decoder Decoded Attributes | ✓ | 72.87 | 39.88 | 0.785 |
| 10 | GSC-17 (T) | Pose + Latent Queries | 7 pose + 17 query = 24 (96 B) | Latent Queries | ✓ | 72.38 | 42.26 | 0.189 |
Attribute controls. As requested by reviewers 3VWs and bVkA, row 5 provides the decoded-attribute, SIC-T, stacking control: 41.19 mIoU at 0.206 MiB, versus 38.91 at 0.196 MiB for the separately trained no-stacking row 4. Reproduced VOGS-L (row 0) does not retain unmatched neighbor Gaussians. Row 1 further reaches 41.90 mIoU at 0.976 MiB using decoded attributes without SIC. Thus, strong gains over VOGS-L are possible without transmitting latent queries; they cannot all be attributed to latent communication.
Fusion pathway. Rows 6/8 and 7/9 transmit the same pose-plus-96-D-query format and use the same SIC and stacking settings within each pair. The direct-query-fusion settings achieve 3.41 and 2.76 more mIoU points, respectively, than decoding the queries into attributes before fusion, with lower measured CV in both comparisons. This supports the latent fusion pathway. Unlike row 5, rows 8–9 still transmit queries and decode them only after reception. The separately trained pairs therefore do not isolate the value of query transmission itself.
Communication budget. The 17-D latent token in row 10 has the same 24-float length as the attribute token in row 5. At similar total CV, it reaches 42.26 versus 41.19 mIoU (0.189 versus 0.206 MiB), while binary IoU is lower (72.38 versus 73.29). For Jsx7's proposed N-protocol attribute control, row 1 achieves mIoU close to the 112-D latent T setting in row 3 (41.90 versus 42.03); row 3 uses about 21% less CV, but also changes the SIC protocol. From row 2 to row 3, CV falls from 0.914 to 0.773 MiB while mIoU falls by 0.44 points. These results support the complete compact-latent design's semantic-mIoU/communication trade-off, rather than a universal advantage attributable to the representation alone.
Official Comment 1: Corrected CV and updated main results
We first provide corrected communication-volume (CV) results for PEQC-compressed GSCollab in the manuscript's table layout for easy comparison. We address the reviewers' questions in subsequent official comments. PEQC CV previously counted 128-dimensional queries reconstructed after reception rather than the compressed queries transmitted. The code correction changes byte accounting, not the trained models or prediction logic. We reevaluated the reported settings on the full validation split using their existing checkpoints; pose and packed SIC-request bytes remain included. Independent evaluations can yield different IoU/mIoU, so each updated accuracy value is reported with the CV measured in the same evaluation. Accuracy changes relative to the submission come from reevaluation, not from the byte-count correction. Unchanged baselines retain their manuscript values. The central result remains: compressed SIC settings exceed VOGS-L in semantic mIoU at lower CV.
CV is MiB per collaborative frame; IoU/mIoU are percentages. Slash-separated cells use
CV/IoU/mIoU. N: no SIC; I: SIC at inference only; T: SIC in training and inference.✓: stacking;✓→--: stacking only during training. GSCollab-128 omits PEQC.Table 2. Semantic-OPV2V fusion and communication controls
Table 5. Co3SOP operating points (
CV/IoU/mIoU)Table 8. SIC versus entropy-confidence gating
Table 9. Semantic-OPV2V operating points (
CV/IoU/mIoU)Table 10. Semantic-OPV2V erasure sweep (
CV/IoU/mIoU)Table 10, CoHFF feature-sparsification reference (unchanged)