MonoSplat：基于单目深度基础模型的可泛化三维高斯泼溅
MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models
AI总结：
针对现有可泛化三维高斯泼溅方法泛化性不足的问题，提出MonoSplat框架，通过单目-多视角特征适配器与集成高斯预测模块融合单目深度先验，在少参数下实现更优的新场景重建质量与效率。
摘要：
可泛化三维高斯泼溅技术的最新进展已在无需逐场景优化的实时高保真渲染方面展现出可观成果，但现有方法因泛化能力有限，在对新场景进行推理时仍难以处理陌生视觉内容。为解决这一挑战，我们提出MonoSplat这一新型框架，它利用预训练单目深度基础模型的丰富视觉先验实现鲁棒的高斯重建。该方法包含两个核心组件：单目-多视角特征适配器（将单目特征转换为多视角表征），以及集成高斯预测模块（有效融合两类特征以生成精准高斯）。借助适配器的轻量级注意力机制，特征在不同视角间实现无缝对齐与聚合，同时保留了宝贵的单目先验，使预测模块能够生成具备准确几何结构与外观的高斯基元。通过在多样化真实世界数据集上开展的大量实验，我们有力证明，MonoSplat在保持计算效率且仅需极少可训练参数的情况下，相比现有方法实现了更优的重建质量与泛化能力。代码可在https://github.com/CUHK-AIM-Group/MonoSplat获取。
英文摘要：
Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content during inference on novel scenes due to limited generalizability. To address this challenge, we introduce MonoSplat, a novel framework that leverages rich visual priors from pre-trained monocular depth foundation models for robust Gaussian reconstruction. Our approach consists of two key components: a Mono-Multi Feature Adapter that transforms monocular features into multi-view representations, coupled with an Integrated Gaussian Prediction module that effectively fuses both feature types for precise Gaussian generation. Through the Adapter's lightweight attention mechanism, features are seamlessly aligned and aggregated across views while preserving valuable monocular priors, enabling the Prediction module to generate Gaussian primitives with accurate geometry and appearance. Through extensive experiments on diverse real-world datasets, we convincingly demonstrate that MonoSplat achieves superior reconstruction quality and generalization capability compared to existing methods while maintaining computational efficiency with minimal trainable parameters. Codes are available at https://github.com/CUHK-AIM-Group/MonoSplat.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
