Sphinx：通过回归引导的选择性细化高效服务新颖视图合成
Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement
AI总结：
Sphinx通过回归引导的选择性细化方法，在显著降低计算成本的同时实现高质量新颖视图合成
摘要：
新颖视图合成（NVS）的任务是从原始输入中未包含的视角生成新图像。基于扩散的NVS可以生成高质量且时间一致的图像，然而仍然计算上不可行。相反，基于回归的NVS尽管计算需求显著较低，但生成质量却不理想，留下设计一个高质量且推理高效的NVS框架的挑战。为填补这一关键差距，我们提出了Sphinx，一个无需训练的混合推理框架，其在显著降低计算成本的情况下实现了扩散级的保真度。Sphinx提出使用基于回归的快速初始化来引导并减少扩散模型的去噪工作量。此外，它集成了选择性细化与自适应噪声调度，使更多计算资源分配给不确定区域和帧。这使Sphinx能够提供灵活的性能-质量权衡导航，适应动态变化的推理场景中的延迟和保真度需求。我们的评估显示，Sphinx在扩散模型推理上平均实现了1.8倍的加速，感知退化小于5%，在NVS服务中建立了质量与延迟之间的新帕累托前沿。
英文摘要：
Novel View Synthesis (NVS) is the task of generating new images of a scene from viewpoints that were not part of the original input. Diffusion-based NVS can generate high-quality, temporally consistent images, however, remains computationally prohibitive. Conversely, regression-based NVS offers suboptimal generation quality despite requiring significantly lower compute; leaving the design objective of a high-quality, inference-efficient NVS framework an open challenge. To close this critical gap, we present Sphinx, a training-free hybrid inference framework that achieves diffusion-level fidelity at a significantly lower compute. Sphinx proposes to use regression-based fast initialization to guide and reduce the denoising workload for the diffusion model. Additionally, it integrates selective refinement with adaptive noise scheduling, allowing more compute to uncertain regions and frames. This enables Sphinx to provide flexible navigation of the performance-quality trade-off, allowing adaptation to latency and fidelity requirements for dynamically changing inference scenarios. Our evaluation shows that Sphinx achieves an average 1.8x speedup over diffusion model inference with negligible perceptual degradation of less than 5%, establishing a new Pareto frontier between quality and latency in NVS serving.
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。
