- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes UniOcean, a generative Gaussian splatting framework for underwater 3D reconstruction under diverse scattering conditions. The method combines Adaptive Particle Modeling, which estimates absorption and scattering using a neural attenuation function, with Progressive Gaussian Generation, which generates additional texture Gaussians from coarse representations. A pretrained diffusion model provides guidance for recovering high-frequency details. Experiments on three underwater benchmarks demonstrate competitive reconstruction performance.
Critical strengths
-
Relevant motivation. The paper addresses the challenges of underwater 3D reconstruction, particularly light attenuation, scattering, and loss of fine-grained textures.
-
Reasonable framework design. Combining attenuation modeling, coarse-to-fine Gaussian representations, and generative guidance is a potentially useful approach to improving underwater reconstruction.
-
Competitive experimental results. The method achieves strong PSNR, SSIM, and LPIPS results across three datasets. The component and loss ablations provide some evidence for the effectiveness of the proposed framework.
Critical weaknesses
-
Weak theoretical motivation for progressive Gaussian generation. The paper attributes insufficient high-frequency reconstruction to an inherent low-frequency bias of Gaussian kernels. However, this explanation is not rigorously established, particularly since Gaussian splatting can represent high-frequency details through sufficiently small and dense primitives. Furthermore, the generated texture Gaussians reuse the positions of coarse Gaussians, raising questions about their ability to recover missing geometric details. More direct comparisons with established Gaussian densification and multiscale strategies may be needed to justify the proposed mechanism.
-
Insufficient validation of generative guidance and reconstruction consistency. The method uses diffusion-refined novel views as auxiliary supervision, but diffusion models may introduce plausible yet inaccurate textures. Although the authors use LPIPS supervision to reduce this risk, no quantitative experiments directly assess hallucination, geometric consistency, or cross-view consistency. Moreover, the claim of handling dynamic underwater scenes is not supported by explicit temporal modeling or temporal-consistency evaluation. These issues weaken the claims regarding high-fidelity reconstruction across diverse conditions.
-
Experimental and presentation limitations. The evaluation covers only 12 scenes, with limited analysis of challenging conditions such as severe turbidity and spatially varying attenuation. The efficiency comparison also shows that UniOcean requires more training time and memory and achieves lower rendering speed than several competing 3DGS methods. In addition, some methodological details and figures require clarification, particularly the generation and optimization of texture Gaussian attributes and the training procedure for generative guidance.
Questions for authors
-
Why is generating additional texture Gaussians at existing coarse Gaussian positions preferable to conventional densification or multiscale Gaussian representations?
-
How is the accuracy and multi-view consistency of diffusion-generated textures evaluated?
-
Can the authors provide a more comprehensive analysis of reconstruction quality versus computational complexity, particularly compared with 3D-USE and 3D-UIR?
3 comments
Official Response by Authors – Part 2
Weakness 2 & Question 2: Insufficient validation of generative guidance and reconstruction consistency.
Answer: Thank you for your constructive comments. We address these concerns from the following two aspects.
(1) Validation of generative guidance and multi-view consistency. We would like to clarify that our UniOcean introduces an LPIPS-based perceptual loss to guide the recovery of fine-grained textures, while the reconstruction loss on the original observed views preserves the underlying scene structure and appearance. Moreover, the generative guidance is applied to a shared 3D Gaussian representation rather than independently optimizing individual views. This design helps reduce the risk of introducing hallucinated details while improving high-frequency texture reconstruction. As shown in Tab. 5 and Fig. 7 of the revised paper, removing the generative guidance leads to a 0.26 dB decrease in PSNR and introduces blurring artifacts in the rendered results. These results demonstrate the important contribution of our generative guidance to recovering fine-grained texture details. To further validate reconstruction consistency, we additionally evaluate the rendered clear views using warped LPIPS (wLPIPS) [4] and photometric reprojection loss (Ph-Loss) [5], measuring cross-view consistency from perceptual and photometric-structural aspects, respectively. As shown in Tab. R2, our UniOcean achieves lower values on both metrics across different scenes, indicating smaller cross-view consistency errors. We have included this table and related discussion in the revised version.
Table R2: Evaluation of multi-view consistency across different scenes.
| Method | Sea-NeRF | U-IW | S-U | |||
|---|---|---|---|---|---|---|
| wLPIPS | Ph-Loss | wLPIPS | Ph-Loss | wLPIPS | Ph-Loss | |
| WaterSplatting | 0.402 | 0.227 | 0.414 | 0.232 | 0.396 | 0.227 |
| SeaSplat | 0.413 | 0.230 | 0.426 | 0.236 | 0.404 | 0.231 |
| 3D-UIR | 0.402 | 0.221 | 0.405 | 0.228 | 0.387 | 0.218 |
| 3D-USE | 0.359 | 0.194 | 0.412 | 0.230 | 0.396 | 0.226 |
| UniOcean (Ours) | 0.357 | 0.194 | 0.382 | 0.213 | 0.371 | 0.206 |
(2) Evaluation of temporal consistency. We would like to clarify that our UniOcean does not explicitly model temporal deformation. Instead, we adopt a more general generative refinement strategy to suppress reconstruction artifacts caused by object motion and inconsistent observations. Similar benefits of diffusion-guided refinement have been demonstrated in previous studies, such as Splat4D [6]. To evaluate temporal consistency, we employ the Tem-Con metric following [7], which computes the average cosine similarity between CLIP features of consecutive frame pairs. As shown in Tab. R3, our method achieves higher similarity scores, indicating better temporal consistency. We have included this table and related discussion in the revised version.
Table R3: Evaluation of temporal consistency in U-IW scenes.
| Method | Tem-Con |
|---|---|
| WaterSplatting | 0.924 |
| SeaSplat | 0.921 |
| 3D-UIR | 0.923 |
| 3D-USE | 0.926 |
| UniOcean (Ours) | 0.927 |
[4] StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning, CVPR 2022.
[5] Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing, ECCV 2026.
[6] Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation, SIGGRAPH 2025.
[7] FateZero: Fusing Attentions for Zero-shot Text-based Video Editing, ICCV 2023.
Official Response by Authors – Part 3
Weakness 3 & Question 3: Experimental and presentation limitations.
Answer: We thank the reviewers for these constructive suggestions. Our detailed responses to the comments are provided as follows.
(1) Additional experiments on more challenging scenes. As suggested, we have conducted additional experiments on the DRUVA dataset, which includes severe turbidity and spatially varying attenuation. As reported in Tab. R4, our method outperforms competing methods on most evaluation metrics in reconstruction quality under these challenging conditions. Meanwhile, the updated Fig. 5 of the revised paper further demonstrates that our method more effectively mitigates underwater attenuation effects. These tables and related discussion are included in the revised version.
Table R4: Quantitative comparison of different methods on the DRUVA dataset.
| Method | A2 | A4 | A5 | A13 | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| PSNR | SSIM | LPIPS | PSNR | SSIM | LPIPS | PSNR | SSIM | LPIPS | PSNR | SSIM | LPIPS | |
| WaterSplatting | 26.58 | 0.850 | 0.337 | 29.63 | 0.859 | 0.364 | 26.22 | 0.832 | 0.354 | 33.07 | 0.965 | 0.356 |
| SeaSplat | 25.79 | 0.853 | 0.342 | 27.06 | 0.857 | 0.388 | 25.51 | 0.846 | 0.348 | 27.21 | 0.957 | 0.417 |
| Plenodium | 25.92 | 0.855 | 0.326 | 28.83 | 0.861 | 0.352 | 26.17 | 0.848 | 0.340 | 30.26 | 0.961 | 0.352 |
| 3D-UIR | 28.65 | 0.865 | 0.304 | 30.58 | 0.869 | 0.343 | 27.35 | 0.854 | 0.322 | 34.43 | 0.964 | 0.348 |
| 3D-USE | 26.10 | 0.846 | 0.344 | 29.39 | 0.856 | 0.371 | 25.99 | 0.823 | 0.368 | 32.74 | 0.964 | 0.360 |
| UniOcean (Ours) | 28.81 | 0.867 | 0.296 | 30.77 | 0.875 | 0.338 | 27.43 | 0.858 | 0.319 | 34.62 | 0.965 | 0.340 |
(2) Analysis of reconstruction quality versus computational complexity. We acknowledge that UniOcean requires additional training time and GPU memory and achieves a lower rendering speed compared with several existing 3DGS-based methods, as shown in Tab. 12 of the paper. This is mainly because the generative guidance introduces additional computational costs during training, while the texture Gaussians increase the number of primitives to be optimized. Compared with 3D-USE and 3D-UIR, our method exhibits certain limitations in computational efficiency. Nevertheless, these additional computational costs enable UniOcean to recover finer texture details and achieve higher reconstruction quality. Considering the trade-off between reconstruction quality and computational efficiency, we believe that the additional computational overhead is acceptable, as efficiency limitations can be partially alleviated by more powerful hardware, whereas improvements in reconstruction quality fundamentally rely on effective methodological designs. We have included this discussion in the revised version.
(3) Clarification of methodological details. 1) Regarding the generation and optimization of texture Gaussian attributes, our PGG first employs multi-resolution hash encoding to extract multi-scale spatial features, as detailed in Eqs. (24)–(26) and Fig. 10. These features are then modulated by the attributes of coarse Gaussians and fed into a multi-head MLP to predict the scales, colors, and opacities of texture Gaussians, as formulated in Eq. (11). During optimization, rather than independently optimizing each texture Gaussian, we update the parameters of the MLPs through backpropagation of the rendering losses, thereby progressively refining the generated Gaussian attributes. 2) Regarding the training procedure for generative guidance, we first synthesize unseen pseudo-views by perturbing the camera poses, as formulated in Eq. (16). These pseudo-views are then fed into a diffusion model to suppress reconstruction artifacts and generate fine-grained details, as described in Eq. (17). Subsequently, the diffusion-refined views provide perceptual guidance through an LPIPS-based loss to optimize the shared 3D Gaussian representation via backpropagation, as formulated in Eq. (21). The collaborative optimization of these two components further facilitates the generation and refinement of texture Gaussians.
Thank you again for your valuable feedback. We have revised the paper to incorporate all related experiments and detailed discussions as you suggested. If there are any additional issues, we are happy to provide further explanations.
Official Response by Authors – Part 1
Thank you for your constructive comments and for helping improve our paper. We have carefully considered and addressed them point by point in the following responses.
Weakness 1 & Question 1: Weak theoretical motivation for progressive Gaussian generation.
Answer: We thank the reviewer for these valuable comments. We provide detailed responses to these concerns as follows.
(1) Explanation of frequency-domain properties. We agree that 3DGS is capable of representing high-frequency details using sufficiently dense and appropriately scaled Gaussian primitives. We would also like to clarify that, due to the inherent low-frequency bias of Gaussian kernels, 3DGS requires more primitives to represent high-frequency details than methods using more suitable kernel functions. However, conventional densification strategies often struggle to meet this requirement due to gradient collisions [1] and improper coupling between Gaussian density and scale [2]. Therefore, 3D reconstruction kernels fundamentally determine the upper bound of densification [3]. This limitation becomes even more pronounced in underwater scenes, where high-frequency information is further suppressed by absorption and scattering effects, making effective Gaussian densification more challenging. These observations motivate our PGG, which generates fine-grained texture Gaussians rather than relying solely on conventional Gaussian densification strategies to learn high-frequency details.
(2) Why reuse the positions? We would like to clarify that reusing the positions of coarse Gaussians is a deliberate design choice, as these positions provide relatively accurate spatial information and are continuously refined during training. Based on these positions, our PGG generates fine-grained texture Gaussians with newly learned attributes, including scales, colors, and opacities, to enhance the representation of local high-frequency details. This design avoids learning Gaussian positions from scratch, thereby accelerating convergence and improving fine-grained texture generation.
(3) Comparison with existing densification strategies. To further validate the effectiveness of PGG, we conduct additional comparisons on the SeaThru-NeRF dataset against the original Gaussian densification strategy from 3DGS, the frequency regularization strategy from FreGS [4], and the multiscale densification strategy from ResGS [4]. As shown in Tab. R1 and Fig. 12 of the revised paper, simply increasing the number of Gaussians, introducing frequency regularization, or adopting multiscale densification does not achieve the same reconstruction quality as our PGG. This is mainly because these methods are primarily designed for reconstruction under relatively clear imaging conditions, without explicitly accounting for the severe visual degradation caused by underwater attenuation. In contrast, our PGG progressively generates fine-grained texture Gaussians, enabling more effective recovery of high-frequency details in underwater scenes. We have included this table and related discussion in the revised version.
Table R1: Ablation study of different densification strategies.
[1] AbsGS: Recovering Fine Details for 3D Gaussian Splatting, ACM MM 2024.
[2] Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting, AAAI 2025.
[3] Revisiting 3D Reconstruction Kernels as Low-Pass Filters, CVPR 2026.
[4] FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization, CVPR 2024.
[5] ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery, ICCV 2025.