DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
This work addresses overfitting in 3D Gaussian Splatting for sparse-view novel view synthesis, which is an incremental improvement for computer vision and graphics applications.
The paper tackles the problem of 3D Gaussian Splatting's performance degradation and artifacts in sparse-view rendering by proposing DropoutGS, which uses Random Dropout Regularization and Edge-guided Splitting Strategy to reduce overfitting and enhance details, achieving state-of-the-art results on benchmark datasets like Blender, LLFF, and DTU.
Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/.