- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces FullSplat, a method for completing driving scenes using 3D Gaussian Splatting (3DGS). The approach identifies object surfaces likely to be revealed in the future, as well as currently occluded background regions. It then leverages structured 3D priors to generate Gaussian residuals within the local coordinate systems of objects, while employing a masked rectified flow model to complete the background in the world coordinate system. Experiments on the Waymo and nuScenes datasets demonstrate improvements in novel-view reconstruction, and experiments involving rigid-body manipulation on the Waymo dataset also show enhanced performance.
Critical strengths
- The problem is clearly defined and represents an important issue within the field.
- The idea of \textit{query-guided target selection} is novel and intuitive.
- The experimental metrics are competitive, and the ablation studies are thorough.
Critical weaknesses
- In query-guided target selection, reconstruction priority is linked to projected area. This may creates an inherent bias: some key NPCs with smaller projected areas(pedestrians, traffic sign) are at a disadvantage compared to objects with larger projected areas(vehicles).
- The contribution of this paper is the \textit{completion of unseen geometry}. However, all metrics used for novel-view synthesis and editing are either distribution-based or reference-free. In other words, the evaluation focuses on an indirect metric rather than the actual effectiveness of the geometric completion itself.
- The computational overhead of the method was not quantified.
Questions for authors
- How are the projected area components unified across different objects?
- What’s the accuracy of completed geometry
- Will FullSplat add notable computational cost, or reduce it?