Score: 1

Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement

Published: November 24, 2025 | arXiv ID: 2511.18672v1

By: Yuchen Xia , Souvik Kundu , Mosharaf Chowdhury and more

Potential Business Impact:

Makes 3D scenes look real, super fast.

Business Areas:
Visual Search Internet Services

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.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
15 pages

Category
Computer Science:
CV and Pattern Recognition