3D Gaussian splatting method reduces data size while keeping quality
ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
Computer Vision and Pattern Recognition
Summary
Creating 3D views from images usually requires lots of tiny dots called Gaussians, which can become excessive and less accurate when training computers to make new views. The authors propose a way to tell the computer which dots to keep or split based on deeper 3D shape clues instead of just surface details. This technique also checks multiple views together to avoid mistakes from a single view's quirks. Their approach reduces the number of dots by over half without losing the realistic look of the images.
What this means in practice
- •For computer graphics developers: Optimize 3D scene representations with fewer Gaussians to speed up real-time rendering and reduce storage needs.
- •For augmented reality app developers: Create more compact 3D models for AR devices that maintain visual quality while saving memory and bandwidth.
Authors
Houqiang Zhong, Tianchi Zhu, Qiang Hu, Xiaoyun Zhang, Li Song, Wenjun Zhang
Abstract
3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time photorealistic novel view synthesis. However, its training-time densification remains largely heuristic, often resulting in redundant Gaussian proliferation and inaccurate geometric reconstruction. Existing methods predominantly rely on first-order screen-space gradients to trigger cloning and splitting, which fail to distinguish true geometric discontinuities from high-frequency textures or noisy residuals. To address this limitation, we propose ACD-GS, an Asymmetric Curvature-aware Densification framework for compact and geometry-aware 3D Gaussian optimization. Our key insight is that second-order depth responses provide a more reliable structural prior for density control, enabling asymmetric regulation of cloning and splitting to better capture geometric discontinuities. Building on this, we introduce a multi-view photometric consistency constraint to suppress transient single-view errors, together with a capacity-aware adaptive regulation strategy that balances densification and pruning during training. Unlike post-hoc compression or quantization-based approaches, ACD-GS directly prevents redundant Gaussian generation during training, yielding inherently compact representations. Extensive experiments demonstrate that our method reduces nearly 60% of Gaussian count and storage while maintaining competitive rendering fidelity, consistently outperforming existing methods across multiple datasets. Our code is available in https://waveviewer.github.io/ACD-GS/.