EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction

Dongrui Dai, Yuxiang XingCVPR 2025 · DOI

Introduction

3D Gaussian Splatting (3DGS) has emerged as a transformative technique for real-time scene reconstruction. However, its performance is heavily dependent on the quality of its initial state. Typically, 3DGS initializes its Gaussians using a point cloud generated via Structure-from-Motion (SfM). In "few-shot" scenarios—where only a limited number of images are available—traditional SfM methods often fail to produce a sufficiently dense point cloud, leading to a "cold start" problem that degrades final reconstruction quality.

The Cold Start Problem in Few-Shot 3DGS

In few-shot settings, standard SfM tools like COLMAP are highly restrictive, often discarding points not visible in at least three views to ensure geometric accuracy. This results in a sparse, "holey" initial point cloud. During the 3DGS optimization phase, the system attempts to compensate by over-expanding the few available Gaussians to fill these gaps. This leads to the creation of "floaters" and significant blur, particularly in regions with weak textures or peripheral areas.

Baseline 3DGS reconstruction from sparse initialization (138 points) showing significant blur and artifacts in the zoomed-in crops.

Methodology: Attentional Pointcloud Augmentation (APA)

EAP-GS addresses this bottleneck by focusing on initialization rather than complex optimization regularizations. The core of the method is Attentional Pointcloud Augmentation (APA), which proceeds in three stages:

  1. Detector-free SfM: The pipeline begins with a modern SfM approach that handles low-texture areas more robustly than traditional SIFT-based methods.
  2. Density Analysis: Using DBSCAN clustering, the system identifies "attention regions" where the current point cloud is sparse despite the presence of complex scene structures.
  3. Relaxed Triangulation: In these identified regions, the algorithm relaxes standard constraints to allow the generation of 3D points from two-view tracks. While these points are slightly less accurate than three-view tracks, they serve as vital geometric anchors in previously empty spaces.
EAP-GS reconstruction using an augmented point cloud (4259 points), resulting in significantly sharper details and fewer artifacts compared to the baseline.

Results and Performance

The EAP-GS method was evaluated on standard benchmarks including LLFF (3-view setting) and Mip-NeRF360 (12-view setting).

  • Reconstruction Quality: On the LLFF dataset, EAP-GS achieved a PSNR of 18.93, a substantial improvement over the 14.63 PSNR of original 3DGS. It matches or exceeds other state-of-the-art few-shot methods like FSGS and CoR-GS.
  • Efficiency: A key advantage of EAP-GS is its speed. On the LLFF benchmark, it reached convergence in just 1.75 minutes, significantly faster than FSGS (25.49 minutes) and CoR-GS (14.96 minutes).
  • Visual Fidelity: The method excels at reconstructing surfaces with weak textures, such as white walls and ceilings, where traditional SfM typically fails to find matches.

Discussion and Conclusion

EAP-GS demonstrates that for few-shot 3DGS, a slightly noisier but significantly denser initial point cloud is preferable to a sparse, "perfect" one. The optimization process is capable of refining Gaussian positions if they are distributed effectively at the start. By prioritizing intelligent initialization through APA, EAP-GS provides a computationally efficient path to high-quality scene reconstruction from limited viewpoints. Future work may explore incorporating generative priors to handle even more extreme cases of 1 or 2 views.

Summary updated

BibTeX
@inproceedings{dai2025eap,
  author = {Dongrui Dai and Yuxiang Xing},
  title = {{EAP-GS: Efficient Augmentation of Pointcloud for 3D Gaussian Splatting in Few-shot Scene Reconstruction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2025},
  doi = {10.1109/cvpr52734.2025.01538},
}
Figure