- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
EviSplat combines instance observation banks and a Gaussian evidence field to preserve multi-view evidence for query-guided open-vocabulary 3D segmentation. Experiments show gains over a reproduced LaGa baseline, with benefits from observation selection and Gaussian-local evidence. However, the novelty is relatively weak compared with prior work, while the learned evidence field and reliability weighting offer only modest gains over sparse empirical distributions and unweighted fusion.
Critical strengths
- The controlled ablations isolate the contribution of top-β observation selection through comparisons with mean and max pooling.
- The component analysis separately evaluates Gaussian-local evidence and fixed-mass aggregation, helping distinguish the contributions of local evidence and aggregation design.
- EviSplat is less sensitive to source-feature corruption.
- The D=16 Gaussian evidence field matches sparse empirical distributions in accuracy while reducing local representation storage.
Critical weaknesses
- Instance observation banks and top-β observation selection overlap with the per-view CLIP embeddings and top-k relevance averaging of https://arxiv.org/abs/2509.12938. Their distinct contribution remains insufficiently isolated.
- Most baseline results are cited as reported. The claimed 5.1-point lead involves different query protocols and lacks matched re-evaluation; the controlled LaGa comparison provides stronger evidence.
- The learned Gaussian evidence field offers limited accuracy gains over sparse empirical distributions despite higher local storage and query costs.
- Observation reliability provides limited additional gains: removing or modifying reliability weighting has little effect on performance in the reported single-run ablations.
- Gains are uneven across datasets and scenes, with marginal improvement on 3D-OVS and degraded performance on RAMEN after adding Gaussian-local evidence. These failure cases remain insufficiently explained.
Questions for authors
- How does https://arxiv.org/abs/2509.12938’s top-k relevance averaging compare with top-β observation selection under the same LaGa backbone, masks, CLIP encoder, grouping, and post-processing?
- What are the total storage and end-to-end query latency for D=16, D=32, and sparse empirical distributions?
- Given that β was selected on LERF-OVS, how were γ and T selected? Are the results robust when these parameters are chosen using held-out scenes or datasets?
- Would the strongest baselines in Tables 1 and C.1 retain their reported rankings under matched backbones, query granularity, post-processing, and averaging conventions?
2 comments
We sincerely thank the reviewer for the thoughtful follow-up and for raising the rating. It has been a privilege to strengthen our paper through your insightful feedback, and we are very glad that the additional experiments addressed your main concerns. Please feel free to reach out if there are any further points you would like to discuss. We wish you a wonderful day!
Thank the authors for the additional experiments, which address my main concerns about the controlled comparisons, hyperparameter selection, and computational costs. I still have concerns about novelty, as prior work already retains multi-view features and combines their relevance scores for each query. Nevertheless, this work provides a marked improvement, and I appreciate the empirical value of this simple yet effective extension. On balance, given the convincing experimental evidence provided in the rebuttal, I tend to raise my rating to 3 (Weak acceptance), while retaining my reservations about the technical novelty.