- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents NGMS, a compact framework for static and dynamic scene reconstruction. It stores a small set of base Gaussians and uses a shared residual field to generate multiple local Gaussians, reducing storage and nonlinear computation while remaining compatible with standard Gaussian rasterization. Experiments on four benchmarks show that NGMS achieves the smallest model sizes among evaluated methods, with competitive reconstruction quality and real-time rendering.
Critical strengths
- NGMS substantially reduces model size while maintaining reasonable reconstruction quality and real-time rendering performance, which is beneficial for deploying Gaussian Splatting on edge devices.
- The residual mixture design provides a unified approach to modeling geometry, appearance, and dynamics while remaining compatible with the standard Gaussian rasterization pipeline.
Critical weaknesses
- Insufficient comparison with recent state-of-the-art methods. The experiments mainly compare against established or relatively older methods, without sufficient evaluation against recent state-of-the-art approaches in compact Gaussian representations and dynamic scene reconstruction. This makes it difficult to determine whether NGMS provides a meaningful improvement over the current state of the art.
- Limited reproducibility and experimental presentation. The code link provided in the paper is currently inaccessible, making it difficult to verify the implementation and assess the reproducibility of the reported results. In addition, the paper provides relatively few qualitative visualizations and experimental figures, which limits the reader’s ability to visually assess reconstruction quality and the practical advantages of the proposed method. For a computer vision paper, stronger qualitative and visual evidence would be expected.
Questions for authors
- For static scenes, how does NGMS compare with recent compression methods such as HAC++: Towards 100X Compression of 3D Gaussian Splatting and Optimized Minimal 3D Gaussian Splatting? These methods can achieve comparable or even better compression and reconstruction performance. Could the authors clarify what the key advantage of NGMS is over these approaches under comparable storage and rendering constraints?
- For dynamic scenes, how does NGMS compare with recent methods such as Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model? Light4GS appears to achieve comparable or even better performance in terms of compression and reconstruction quality. Could the authors provide a detailed comparison and clarify what advantages NGMS offers over such recent approaches?
- Could the authors provide more qualitative visual results to better support the claimed advantages of NGMS? The current paper contains relatively few visualization results, making it difficult to assess the visual quality of reconstruction and the effectiveness of the proposed representation, particularly for fine geometry, view-dependent appearance, and dynamic deformation.
3 comments
2. Orthogonality and integration benefits. The reviewer's suggestions also motivated us to examine an integration benefit of our design. NGMS reduces learnable parameters within this unified formulation: complete diffuse bases and a shared field generate multiple residual Gaussians per base. Appendix B.2 reports the base/field storage breakdown. Quantization and coding can then compress the remaining bases and field weights, creating an opportunity to benefit from the compression techniques highlighted by the reviewer.
We use default quantization because it substantially reduces storage while changing mean PSNR by only about 0.01-0.02 dB across all four datasets. This setting uses INT8 color, opacity, and rotation, with FP16 scales and field weights. Extended quantization additionally uses INT8 scales and network weight rows.
Retaining complete, explicit base Gaussian attributes supports compatibility with standard Gaussian rasterizers and attribute-based processing tools. We integrate G-PCC position coding at voxel step 0.001, using only the geometry coding stage of HAC++, as post-processing without retraining. The HAC++ scene-specific hash-grid context model and rate loss are not applied. This integration illustrates the practical benefit of our Gaussian-native design.
The following additional post-compression experiment covers all four datasets. Each cell reports PSNR (dB) / size (MB). Dynamic experiments use the paper's 2x downsampling.
| NGMS setting | NeRF Synthetic | Mip-NeRF 360 | D-NeRF | N3V |
|---|---|---|---|---|
| Before post-compression | 33.56 / 4.477 | 27.44 / 19.627 | 40.53 / 3.461 | 31.38 / 24.605 |
| Default quantization | 33.55 / 1.868 | 27.43 / 7.985 | 40.51 / 1.500 | 31.37 / 10.003 |
| G-PCC only | 33.42 / 3.838 | 27.39 / 16.376 | 40.43 / 3.151 | 31.36 / 20.552 |
| Default quantization + G-PCC | 33.41 / 1.284 | 27.38 / 5.034 | 40.41 / 1.215 | 31.35 / 6.339 |
| Extended quantization + G-PCC | 33.40 / 0.918 | 27.37 / 4.030 | 40.32 / 0.767 | 31.34 / 5.050 |
On these NGMS checkpoints, default quantization achieves higher PSNR and approximately half the file size of G-PCC geometry coding alone on all four datasets. This supports its use for the main results: it preserves quality while providing substantial storage savings.
For more aggressive compression, combining extended quantization with G-PCC achieves the smallest checkpoints among the tested settings. It reduces storage by a further 49-51% relative to default quantization, with only 0.03-0.19 dB additional mean PSNR loss across the four datasets. NGMS therefore offers both a quality-preserving default and a stronger compression option, enabled by combining learnable parameter reduction with post-compression.
3. Code and reproducibility. We acknowledge that the code is not currently accessible. As stated in our reproducibility statement, we will release the code and data after acceptance. Sections 3-4 and Appendix A provide implementation-level specifications to support reproduction, including network architecture and encodings, residual composition, initialization, optimization and densification schedules, evaluation protocol, and checkpoint format. Because NGMS retains standard Gaussian attributes and rasterization, these details support independent reimplementation within the established open-source Gaussian Splatting ecosystem.
4. Qualitative results.
Following the reviewer's suggestion, we have upgraded Figures 3 and 4 with matching zoom-in crops and absolute RGB error maps. Figure 3 highlights repeated lego studs, thin bonsai branches, and view-dependent reflections against 3DGS and Scaffold-GS. Figure 4 highlights the trex ribcage and hook boundaries against 4DGS and 4D Scaffold-GS. Both include GT and consistent crop regions and error scales. These additions expose localized detail and appearance errors, with NGMS preserving clearer articulated structures and lower errors in the highlighted dynamic regions. Appendix B.1 provides complementary per-scene SSIM and LPIPS results.
Ahead of the discussion deadline, we kindly invite you to check our response and revision.
We have carefully addressed your concerns and added the requested experiments. We remain available if any further clarification is needed.
Thank you again for your time and helpful reviews.
Response to Reviewer R9NA
We thank the reviewer for the thoughtful and constructive suggestions. The requested comparisons, additional compression experiments, and upgraded qualitative figures have strengthened the experimental support for NGMS and helped us explain its practical advantages more clearly.
We have submitted a revised manuscript with expanded discussion and coverage of recent related work (Section 2), improved qualitative comparisons with matching zoom-in crops for fine detail and view-dependent effects, together with error maps (Figures 3 and 4), and a new compression integration experiment demonstrating the benefit of NGMS's Gaussian-native design (Section 4.4). Extended quantization additionally uses INT8 scales and network weight rows; combining it with G-PCC position coding (voxel step 0.001) reduces storage by a further 49-51% relative to default quantization, with only 0.03-0.19 dB additional mean PSNR loss across the four datasets.
1. Additional comparisons. We summarize the requested comparisons with HAC++ (low rate), OMG-M, and Light4GS below, including an additional full-resolution NGMS run on D-NeRF. For the main-text experiments, all methods use the same evaluation protocol, including dataset splits, image resolutions, and metric definitions. In the appendix comparisons, we clearly distinguish results taken from published papers from those obtained in our own runs. Appendix E ("Broader Quality-Storage Comparisons") provides the broader comparisons. In the tables below, baseline values are published results; NGMS values are our runs.
NeRF Synthetic
Mip-NeRF 360
D-NeRF, full resolution
To match Light4GS's full-resolution setting, we trained NGMS at full resolution. Light4GS values are its published low-rate results; Light4GS was not retrained.
These results show that NGMS provides competitive reconstruction quality with compact storage across both static and dynamic scenes. On NeRF Synthetic, NGMS achieves 33.58 dB with a 1.9 MB model. On Mip-NeRF 360, it achieves 27.44 dB at 8.0 MB, remaining within 0.16 dB of HAC++ at comparable storage. On full-resolution D-NeRF, NGMS exceeds the reported Light4GS result by 6.57 dB while reducing storage from 2.20 to 1.64 MB. NGMS achieves these results through a unified base-Gaussian and residual-mixture formulation, with a time branch enabled for dynamics.