Opacity-Gradient Driven Density Control for Compact and Efficient Few-Shot 3D Gaussian Splatting
This work addresses the efficiency and overfitting issues in few-shot 3D view synthesis, establishing a new state-of-the-art on the quality-vs-efficiency Pareto frontier, though it is incremental as it builds on existing 3DGS methods.
The paper tackled the problem of 3D Gaussian Splatting (3DGS) overfitting and inefficiency in few-shot scenarios by revising its optimization to prioritize compactness, achieving over 40% more compact reconstructions on the 3-view LLFF dataset and approximately 70% reduction on the Mip-NeRF 360 dataset with modest trade-offs in quality.
3D Gaussian Splatting (3DGS) struggles in few-shot scenarios, where its standard adaptive density control (ADC) can lead to overfitting and bloated reconstructions. While state-of-the-art methods like FSGS improve quality, they often do so by significantly increasing the primitive count. This paper presents a framework that revises the core 3DGS optimization to prioritize efficiency. We replace the standard positional gradient heuristic with a novel densification trigger that uses the opacity gradient as a lightweight proxy for rendering error. We find this aggressive densification is only effective when paired with a more conservative pruning schedule, which prevents destructive optimization cycles. Combined with a standard depth-correlation loss for geometric guidance, our framework demonstrates a fundamental improvement in efficiency. On the 3-view LLFF dataset, our model is over 40% more compact (32k vs. 57k primitives) than FSGS, and on the Mip-NeRF 360 dataset, it achieves a reduction of approximately 70%. This dramatic gain in compactness is achieved with a modest trade-off in reconstruction metrics, establishing a new state-of-the-art on the quality-vs-efficiency Pareto frontier for few-shot view synthesis.