Papers
arxiv:2602.05293

Fast-SAM3D: 3Dfy Anything in Images but Faster

Published on Feb 5
ยท Submitted by
Weilun Feng
on Feb 6
Authors:
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

Fast-SAM3D addresses slow inference in 3D reconstruction by dynamically adapting computation to varying complexity through heterogeneity-aware mechanisms that improve efficiency without sacrificing quality.

AI-generated summary

SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the first systematic investigation into its inference dynamics, revealing that generic acceleration strategies are brittle in this context. We demonstrate that these failures stem from neglecting the pipeline's inherent multi-level heterogeneity: the kinematic distinctiveness between shape and layout, the intrinsic sparsity of texture refinement, and the spectral variance across geometries. To address this, we present Fast-SAM3D, a training-free framework that dynamically aligns computation with instantaneous generation complexity. Our approach integrates three heterogeneity-aware mechanisms: (1) Modality-Aware Step Caching to decouple structural evolution from sensitive layout updates; (2) Joint Spatiotemporal Token Carving to concentrate refinement on high-entropy regions; and (3) Spectral-Aware Token Aggregation to adapt decoding resolution. Extensive experiments demonstrate that Fast-SAM3D delivers up to 2.67times end-to-end speedup with negligible fidelity loss, establishing a new Pareto frontier for efficient single-view 3D generation. Our code is released in https://github.com/wlfeng0509/Fast-SAM3D.

Community

Paper submitter

image

arXivLens breakdown of this paper ๐Ÿ‘‰ https://arxivlens.com/PaperView/Details/fast-sam3d-3dfy-anything-in-images-but-faster-7451-43eb5231

  • Executive Summary
  • Detailed Breakdown
  • Practical Applications

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2602.05293 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2602.05293 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2602.05293 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.