用自适应高斯点提升3D场景分辨率，实时生成细节。
GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution
- 基于海森采样识别需细化区域，动态添加高斯点。
- 推理速度0.015秒/帧，支持实时交互应用。
- 无需复杂生成模型，适合高保真3D重建场景。
我们提出一种新方法，可超越原始训练分辨率，显著提升3D高斯泼溅（3DGS）的分辨率与几何保真度。现有3DGS方法受限于输入分辨率，无法还原训练视图中未包含的更细粒度细节。本文通过轻量级生成模型，在需要的位置预测并优化额外的3D高斯点，突破此限制。核心创新是海森辅助采样策略，智能识别最可能受益于加密的区域，保证计算效率。相比计算开销大的GAN或扩散模型，本方法可在单张消费级显卡上实现0.015秒/次推理，支持实时应用。大量实验表明，该方法在几何精度和渲染质量上均显著优于当前最优方法，确立了无分辨率限制的3D场景增强新范式。
原文摘要 · Abstract (English)
We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing reconstructions that cannot extrapolate finer details than are present in the training views. Our work breaks this limitation through a lightweight generative model that predicts and refines additional 3D Gaussians where needed most. The key innovation is our Hessian-assisted sampling strategy, which intelligently identifies regions that are likely to benefit from densification, ensuring computational efficiency. Unlike computationally intensive GANs or diffusion approaches, our method operates in real-time (0.015s per inference on a single consumer-grade GPU), making it practical for interactive applications. Comprehensive experiments demonstrate significant improvements in both geometric accuracy and rendering quality compared to state-of-the-art methods, establishing a new paradigm for resolution-free 3D scene enhancement.
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。