- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
CoReSplat enhances the distractor-free 3DGS technique by accumulating historical data on signed residuals across views, constructing geometrically aligned cross-view medians, and applying historical consistency and inconsistency as independent correction terms before calculating the reconstruction loss. The evaluation included two benchmark tests, as well as integration with DeSplat, RobustSplat, and DualSplat.
Critical strengths
-
This correction method employs a modular design and does not introduce dependencies during the inference process.
-
Table 3 shows that PSNR improved across all 33 combinations of methods and scenarios.
-
The results of the ablation experiments confirm the advantages of methods such as consensus-based correction, time accumulation, and supervised weighted history.
Critical weaknesses
-
Compared with related optimization methods (particularly HarmoGS), its added value has not yet been fully demonstrated.
-
Rough and cumulative residual historical data may lead to unreliable consensus, this limitation has not yet been thoroughly verified.
-
Explanations regarding computational complexity and additional training costs remain insufficient.
Questions for authors
-
Is it possible to compare it with HarmoGS under the same settings?
-
How reliable is this consensus mechanism? In static scenarios, can the compensation process preserve useful gradient information?
-
How much training time and memory overhead does CoReSplat incur?