- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes a latent bridge trajectory distillation (LBTD) for 3D Gaussian Splatting super-resolution. It introduces several modules, such as multi-view latent bridge restoration, progressive trajectory distillation, and detail-aware Gaussian splitting, to improve high-resolution rendering quality and cross-view consistency. Experiments demonstrate the effectiveness of the proposed method.
Critical strengths
The LR-anchored restoration trajectory provides an interesting perspective on diffusion-guided 3D super-resolution.
Critical weaknesses
- This method relies on large-scale pre-training to generate backbone, but does not fully analyze the total training cost and memory requirements. In ablation studies, the independent improvements from cross-view adapters and detail-aware segmentation are relatively small.
- The proposed trajectory distillation lacks a deeper theoretical explanation for its superiority over alternative iterative recovery schemes. The robustness of pseudo HR supervision to hallucinatory structures deserves further research.
Questions for authors
Why does the cross view adapter only provide minor improvements in reconstruction metrics? How does trajectory distillation behave when the recovery model produces inaccurate high-frequency details?
7 comments
Question 1
Why does the cross view adapter only provide minor improvements in reconstruction metrics? How does trajectory distillation behave when the recovery model produces inaccurate high-frequency details?
Response to Question 1
Thank you for raising these questions. As shown above, the cross-view adapter provides smaller PSNR gains on Mip-NeRF360 than on Tanks & Temples after GS optimization. Its improvements to SR supervision may become less pronounced after GS optimization. To assess the adapter’s effect before 3D reconstruction, we compare Single-View SR and Multi-View SR directly on LR input views from four datasets, without subsequent 3DGS optimization:
| Dataset | Method | PSNR↑ | SSIM↑ | LPIPS↓ | NIQE↓ | DISTS↓ | FID↓ |
|---|---|---|---|---|---|---|---|
| Mip-NeRF360 | Single-View SR | 29.09 | 0.8531 | 0.1756 | 6.155 | 0.0899 | 6.51 |
| Mip-NeRF360 | Multi-View SR | 29.34 | 0.8667 | 0.1683 | 5.992 | 0.0900 | 6.44 |
| LLFF | Single-View SR | 29.99 | 0.9020 | 0.0944 | 5.138 | 0.0641 | 5.76 |
| LLFF | Multi-View SR | 30.59 | 0.9063 | 0.0825 | 4.928 | 0.0573 | 3.72 |
| Tanks & Temples | Single-View SR | 25.08 | 0.7892 | 0.1451 | 4.234 | 0.0854 | 11.14 |
| Tanks & Temples | Multi-View SR | 25.46 | 0.7939 | 0.1380 | 4.246 | 0.0804 | 8.55 |
| DL3DV | Single-View SR | 30.85 | 0.8850 | 0.1096 | 5.497 | 0.0576 | 4.84 |
| DL3DV | Multi-View SR | 31.26 | 0.8929 | 0.1002 | 5.181 | 0.0471 | 3.15 |
The adapter improves PSNR by 0.25 dB, 0.60 dB, 0.38 dB, and 0.41 dB on Mip-NeRF360, LLFF, Tanks & Temples, and DL3DV, respectively. It also improves SSIM, LPIPS, and FID across all four datasets, demonstrating its benefits across datasets.
Trajectory distillation uses stage-wise supervision and 3D rendering feedback to update SR predictions alongside the shared 3D representation, rather than fitting fixed SR targets. This allows inaccurate details in early SR predictions to be revised as reconstruction proceeds. In Figure 13, trajectory distillation initially produces distorted shapes of the LEGO stud and wheel, but refines these structures in later stages. In contrast, the fixed pseudo-HR target retains its original errors throughout GS optimization. This example illustrates how trajectory distillation can revise inaccurate SR supervision, rather than repeatedly using the same erroneous SR target.
Final Comment
Thank you for your detailed rebuttal and the additional experiments. First, the authors did not provide a revised manuscript incorporating the new experiments, so it is unclear whether they were unaware of the rebuttal requirements. Without an updated version, it is difficult to verify how these issues were addressed in the paper. Second, I cannot find a disclosure statement regarding the use of LLMs or AI in the manuscript, , and Figure 2 appears to rely heavily on AI-generated visual content. I am concerned about whether this complies with the ICLR guidelines and whether it might be rejected.
Regarding the rebuttal, I acknowledge that the additional experiments addressed some of my concerns. However, The improvements were limited, and the computational overhead was significant. The benefits of detail-aware splitting remain relatively modest, and the reported computational analysis did not fully account for the cost of the entire pipeline.
The rationale for trajectory distillation is insufficient. The authors primarily provide intuitive explanations for LR-anchored initialization and stage optimization, but they lack sufficient controlled experiments to demonstrate their respective contributions or to show that they outperform alternative iterative recovery schemes.
Robustness to hallucinated details. Although the qualitative examples in Figure 13 are encouraging, a single example is insufficient to establish the robustness of trajectory distillation to inaccurate or hallucinated structures in pseudo-HR supervision.
Overall, I appreciate the authors’ efforts and acknowledge that some concerns have been partially or substantially addressed. However, due to the lack of a revised draft, the need for clarification regarding key figures, and remaining methodological and robustness issues, I cannot fully endorse the paper’s contributions. Therefore, I maintain my original rating.
Weakness 1
This method relies on large-scale pre training to generate backbone, but does not fully analyze the total training cost and memory requirements. In ablation research, the independent improvement of cross view adapters and detail aware segmentation is relatively small.
Response to Weakness 1
Thank you for raising these concerns. The training of our SR model takes approximately 300 A100 GPU-hours on A100 80GB GPUs. The peak memory usage during training is approximately 66 GiB, with a batch size of 4 images per GPU.
To better examine the improvement of our cross-view adapter and detail-aware splitting, we repeated each configuration with three random seeds on Mip-NeRF360 and Tanks & Temples. We report the mean ± standard deviation:
Mip-NeRF360:
Tanks & Temples:
To assess the cross-view adapter, we compare Single-View SR with Multi-View SR. To assess detail-aware splitting, we compare Multi-View SR + TD with the full model, where TD refers to trajectory distillation. The cross-view adapter improves PSNR by 0.05 dB on Mip-NeRF360 and 0.12 dB on Tanks & Temples, while reducing FID by 1.36 and 1.93, respectively. Detail-aware splitting improves PSNR by 0.04 dB and 0.12 dB, and reduces FID by 0.74 and 0.77, respectively. Thus, the gains remain positive after averaging over three seeds, with larger PSNR gains on Tanks & Temples. The adapter improves SR supervision by sharing complementary information across views, while detail-aware splitting helps the Gaussian representation capture finer structures. They therefore improve different parts of the pipeline and provide complementary gains in reconstruction quality.
Weakness 2
The proposed trajectory distillation lacks a deeper theoretical explanation for its superiority over alternative iterative recovery schemes. The robustness of pseudo HR supervision to hallucinatory structures deserves further research.
Response to Weakness 2
Our proposed trajectory distillation is different from other iterative recovery schemes, like 3DSR, regarding trajectory initialization and the stage-wise sampling schedule.
We discuss the robustness of pseudo-HR supervision to hallucinated structures in our response to the next question.