Lune

CVPR2026Top-tier venue

Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration

Mengyu Yang, Yanming Yang, Chenyi Xu, Chenxi Song, Yufan Zuo, Tong Zhao, Ruibo Li, Chi Zhang

Abstract

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 54.83% reduction in FLOPs, with minimal degradation in geometric quality as measured by Chamfer Distance (2.48%) and F-Score (1.95%).

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Video Diffusion Models cites Denoising Diffusion Probabilistic Models
  • DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps cites Video Diffusion Models
  • DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps cites Denoising Diffusion Probabilistic Models
  • Directly Denoising Diffusion Models cites Video Diffusion Models
  • Directly Denoising Diffusion Models cites DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
  • Directly Denoising Diffusion Models cites Denoising Diffusion Probabilistic Models
  • Scaling Rectified Flow Transformers for High-Resolution Image Synthesis cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Fast-SAM3D: 3Dfy Anything in Images but FasterWeilun Feng, Mingqiang Wu, zhiliang chen, Chuanguang Yang et al.ICML 2026 · 2 citations

Builds on53

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
  3. Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
  4. Video Diffusion ModelsJonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan et al.NeurIPS 2022 · 2,948 citations
  5. DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 StepsCheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen et al.NeurIPS 2022 · 2,653 citations

Related papers

  1. SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware CachingYasaman Haghighi, Alexandre AlahiCVPR 2026 · 5 citations
  2. Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCacheBowen Cui, Yuanbin Wang, Huajiang Xu, Biaolong Chen et al.CVPR 2026 · 6 citations
  3. FasterCache: Training-Free Video Diffusion Model Acceleration with High QualityZhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang et al.ICLR 2025
  4. Revisiting Redundancy in Diffusion Transformers: A Temporal-Spatial Joint Caching Strategy for Efficient SamplingChenxi Du, Yongheng Deng, Ju Ren, Yaoxue ZhangKDD 2026
  5. BWCache: Accelerating Video Diffusion Transformers through Block-Wise CachingHanshuai Cui, Zhiqing Tang, Zhifei Xu, Zhi Yao et al.ICLR 2026 · 11 citations
Dusk over the sea between two cliffs drawn in fine vertical lines