- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper starts from unposed and uncalibrated multi-view thermal infrared images and directly predicts camera parameters, depth, and renderable thermal 3D Gaussians in a feed-forward manner. It addresses a well-defined and practically valuable problem. In addition, the authors introduce ThermalVerse, a dataset comprising 209 scenes and 26,071 paired RGB–thermal images. Overall, I consider both the proposed method and the dataset to be valuable contributions.
Critical strengths
-
The problem setting is relevant and addresses a relatively less explored direction. Prior thermal NeRF / Gaussian Splatting methods typically rely on known camera parameters or per-scene optimization, whereas this work considers a feed-forward setting without these assumptions.
-
The paper also provides a useful data contribution. ThermalVerse contains 209 scenes across 30 content categories, with approximately 26K paired RGB–thermal images.
-
The experimental evaluation is fairly comprehensive, and the reported results provide reasonable empirical support for the proposed method.
Critical weaknesses
-
“Matched AnySplat-IR” is not a strictly architecture-matched baseline. Although the two methods share the same training data and evaluation protocol, they differ in the backbone, encoder, teacher model, and LoRA placement. I suggest clarifying this distinction more explicitly in the main text.
-
The scaling experiments use a fixed training budget of 7,000 steps. As the dataset size increases, the average exposure per scene consequently decreases. The results may therefore be more appropriately interpreted as fixed-compute scaling, rather than as a general scaling law.
-
The main model uses LoRA on both the attention and FFN modules, whereas the scaling and ablation experiments use attention-only LoRA. It would be helpful to briefly explain the motivation for using different configurations and to clarify that these results are not obtained under exactly the same model setting.
Questions for authors
-
Could the authors clarify more explicitly which settings are matched in “Matched AnySplat-IR” and which architectural components still differ between the two methods?
-
How do the authors view the effect of fixing the training budget at 7,000 steps on the scaling results? Would it be more appropriate to characterize these experiments as fixed-compute scaling?
-
Why does the main model use attention+FFN LoRA, while the scaling and ablation experiments use attention-only LoRA? How should the results under these two configurations be interpreted in relation to each other?