# SmileSplat: Generalizable Gaussian Splats for Unconstrained Sparse Images

arXiv: https://arxiv.org/abs/2411.18072 · HTML: https://mlsanity.com/paper/2411.18072/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2024.

## Built on by (most cited first, 4 of 4)

- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [Learnable Infinite Taylor Gaussian for Dynamic View Rendering](https://mlsanity.com/paper/2412.04282/) (2024)
- [CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Model](https://mlsanity.com/paper/2511.13121/) (2025)
- [XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method](https://mlsanity.com/paper/2510.07856/) (2025)

## Abstract (arXiv)

Sparse Multi-view Images can be Learned to predict explicit radiance fields via Generalizable Gaussian Splatting approaches, which can achieve wider application prospects in real-life when ground-truth camera parameters are not required as inputs. In this paper, a novel generalizable Gaussian Splatting method, SmileSplat, is proposed to reconstruct pixel-aligned Gaussian surfels for diverse scenarios only requiring unconstrained sparse multi-view images. First, Gaussian surfels are predicted based on the multi-head Gaussian regression decoder, which can are represented with less degree-of-freedom but have better multi-view consistency. Furthermore, the normal vectors of Gaussian surfel are enhanced based on high-quality of normal priors. Second, the Gaussians and camera parameters (both extrinsic and intrinsic) are optimized to obtain high-quality Gaussian radiance fields for novel view synthesis tasks based on the proposed Bundle-Adjusting Gaussian Splatting module. Extensive experiments on novel view rendering and depth map prediction tasks are conducted on public datasets, demonstrating that the proposed method achieves state-of-the-art performance in various 3D vision tasks. More information can be found on our project page (https://yanyan-li.github.io/project/gs/smilesplat)