Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
This addresses computational inefficiency in 3D generative AI for applications like graphics and simulation, but it is incremental as it builds on existing caching methods for 2D/video.
The paper tackled the problem of slow inference in 3D diffusion models due to iterative denoising, proposing Fast3Dcache to accelerate 3D geometry synthesis while preserving geometric fidelity, achieving up to a 27.12% speed-up and 54.8% reduction in FLOPs with minimal quality degradation.
Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoising process. While recent caching-based methods effectively reuse redundant computations to speed up 2D and video generation, directly applying these techniques to 3D diffusion models can severely disrupt geometric consistency. In 3D synthesis, even minor numerical errors in cached latent features accumulate, causing structural artifacts and topological inconsistencies. To overcome this limitation, we propose Fast3Dcache, a training-free geometry-aware caching framework that accelerates 3D diffusion inference while preserving geometric fidelity. Our method introduces a Predictive Caching Scheduler Constraint (PCSC) to dynamically determine cache quotas according to voxel stabilization patterns and a Spatiotemporal Stability Criterion (SSC) to select stable features for reuse based on velocity magnitude and acceleration criterion. Comprehensive experiments show that Fast3Dcache accelerates inference significantly, achieving up to a 27.12% speed-up and a 54.8% reduction in FLOPs, with minimal degradation in geometric quality as measured by Chamfer Distance (2.48%) and F-Score (1.95%).