提出不对称3D高斯溅射架构，大幅提升长序列场景建模效率。
AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling
- 分几何与外观两分支，粗粒度与细粒度特征分别处理
- 在960P 32视角下达优化方法水平，速度提升近800倍
- 参数更少、训练推理开销低，适合资源受限场景
近期通用3D高斯溅射模型虽推动了长序列新视角合成（NVS）进展，但伴随大量冗余计算。我们发现冗余源于两点：(i) 高质量NVS并不要求高精度几何；(ii) 外观学习通常比几何恢复更简单。基于此，提出一种不对称架构，解耦几何与外观建模。几何分支以粗粒度令牌为主，使用多数参数进行多视角重建；外观分支则处理细粒度令牌，用极少参数捕捉细节。两分支通过双向连接交互，实现任务间互导。该任务感知的不对称设计减少计算冗余，更合理分配资源，提升参数效率，使小型模型也能表现强劲。在32视角960P输入下，本模型达到基于优化的方法性能，同时实现近800倍加速，且以显著更少参数和更低训练/推理开销超越当前最优通用模型的零样本表现，整体效率显著提升。
原文摘要 · Abstract (English)
Recent generalizable 3D Gaussian Splatting models have advanced long-sequence novel view synthesis (NVS), but at the cost of substantial redundant computation. We identify that the redundancy can be mitigated based on two observations: (i) high-precision geometry is not strictly required for high-quality NVS; (ii) appearance learning is generally easier than geometry recovery. Motivated by these insights, we propose an asymmetric architecture that decouples geometry and appearance modeling. The geometry branch processes coarse-grained tokens with most of the parameters for multi-view reconstruction, while the appearance branch operates on fine-grained tokens to capture details using significantly fewer parameters. The two branches interact through bilateral connections, enabling mutual guidance for their respective tasks. This task-aware asymmetry reduces the computational redundancy and allocates the computation more judiciously, thereby increasing parameter efficiency and enabling smaller models to achieve strong performance. On 32-view 960P inputs, our model matches optimization-based methods while delivering nearly 800x speedup, and surpasses the zero-shot performance of state-of-the-art generalizable models with markedly fewer parameters and reduced training/inference overhead, achieving an overall efficiency improvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。