Improving Adaptive Density Control for 3D Gaussian Splatting

2025-03-18

Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

AI Summary

To address background under-reconstruction and foreground overfitting caused by adaptive density control in 3D Gaussian Splatting (3DGS), this work introduces three novel strategies: (1) geometry-aware scene extent correction to mitigate Gaussian imbalance near boundaries; (2) exponentially increasing gradient threshold scheduling to enhance optimization stability; and (3) rendering-contribution-weighted saliency-aware pruning for semantic-aware primitive simplification. All components are seamlessly integrated into the standard 3DGS pipeline without requiring auxiliary networks or additional supervision. Experiments demonstrate that, at identical Gaussian counts, our method achieves PSNR gains of 1.2–2.4 dB, accelerates training by over 2×, significantly suppresses background artifacts, and improves geometric detail fidelity.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

3D Gaussian Splatting (3DGS) has become one of the most influential works in the past year. Due to its efficient and high-quality novel view synthesis capabilities, it has been widely adopted in many research fields and applications. Nevertheless, 3DGS still faces challenges to properly manage the number of Gaussian primitives that are used during scene reconstruction. Following the adaptive density control (ADC) mechanism of 3D Gaussian Splatting, new Gaussians in under-reconstructed regions are created, while Gaussians that do not contribute to the rendering quality are pruned. We observe that those criteria for densifying and pruning Gaussians can sometimes lead to worse rendering by introducing artifacts. We especially observe under-reconstructed background or overfitted foreground regions. To encounter both problems, we propose three new improvements to the adaptive density control mechanism. Those include a correction for the scene extent calculation that does not only rely on camera positions, an exponentially ascending gradient threshold to improve training convergence, and significance-aware pruning strategy to avoid background artifacts. With these adaptions, we show that the rendering quality improves while using the same number of Gaussians primitives. Furthermore, with our improvements, the training converges considerably faster, allowing for more than twice as fast training times while yielding better quality than 3DGS. Finally, our contributions are easily compatible with most existing derivative works of 3DGS making them relevant for future works.

Problem

• Improves adaptive density control in 3D Gaussian Splatting.
• Addresses artifacts from under-reconstructed and overfitted regions.
• Enhances rendering quality and training speed simultaneously.

Innovation

• Enhanced scene extent calculation using camera-independent metrics
• Exponentially ascending gradient threshold for faster training convergence
• Significance-aware pruning to reduce background artifacts