- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes SplatRefiner, a diffusion-based post-hoc refinement method for sparse-view novel view synthesis. Instead of repeatedly generating novel views and re-optimizing the 3D representation, it directly refines renderings from a fixed Gaussian reconstruction. The method uses VGGT features for reference-view conditioning and target-view alignment, along with dual-condition guidance during inference. Experiments show improved rendering quality and reduced computational cost across multiple datasets and reconstruction methods.
Critical strengths
-
The method avoids repeated reconstruction and generation cycles, which substantially reduces the overall processing time.
-
The experiments cover multiple datasets, Gaussian reconstruction methods, and input-view counts. The results also show that a model trained on 2DGS renderings can generalize to 3DGS and FSGS.
-
The paper examines different locations for VGGT feature injection and alignment. The results provide useful observations about how these components interact.
-
SplatRefiner consistently improves the input renderings and outperforms DIFIX when applied to the same renderings in nearly all evaluated settings.
Critical weaknesses
-
Feature injection, feature alignment, and classifier-free guidance are established techniques. The main contribution appears to be their combination and configuration for post-hoc refinement rather than a fundamentally new method.
-
SplatRefiner substantially outperforms DIFIX, but the two methods use different pretrained diffusion backbones and training configurations. It is therefore difficult to determine how much of the improvement comes from the proposed components. A more controlled comparison would help clarify this.
-
Although the paper provides consistency and correspondence evaluations, it remains unclear how reliably the method preserves the observed scene when the initial rendering contains significant errors. A more detailed analysis of such failure cases would strengthen the faithfulness claim.
-
The comparison between consecutive and random view grouping is useful, but it does not sufficiently evaluate challenging target viewpoints. Additional results under large viewpoint changes or severe disocclusions would strengthen the trajectory-free claim.
Questions for authors
-
Could you clarify the fundamental technical novelty of your method beyond the specific combination and configuration of established techniques (feature injection, alignment, CFG) for post-hoc refinement?
-
Could you provide a controlled comparison or ablation study against DIFIX using the same pretrained diffusion backbone and training configuration to isolate the exact contribution of your proposed components?
-
How reliably does the method preserve the observed scene when the initial rendering contains significant errors? Please provide an analysis of failure cases under these conditions to substantiate the faithfulness claim.
-
To fully support the "trajectory-free" claim, could you provide additional evaluation results under more challenging target viewpoints, such as large viewpoint changes or severe disocclusions?
-
A demo video is needed.
2 comments
Thank you for your careful review and for taking the time to consider our responses and additional experiments. Your constructive feedback has helped us strengthen our experimental validation.
We sincerely appreciate your time and consideration.
Official Comment
I still have some concerns about the novelty and the DIFIX comparison, but the authors have addressed most of my comments. I will keep my rating of weak accept.