Papers
arxiv:2605.06270

Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction

Published on May 18
Authors:
,
,
,
,
,
,
,

Abstract

A training-free acceleration framework compresses query and key-value tokens differently in feed-forward Vision Transformer 3D reconstruction models, enabling large video inputs with substantial speedup while preserving reconstruction quality.

Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains challenging due to the quadratic cost of global attention layers. Recent token-merging methods accelerate these models by compressing the token sequence within the global attention layers, but they apply a uniform reduction to query tokens and key-value tokens, ignoring their functionally distinct roles in 3D reconstruction. In this work, we identify a key property of feed-forward 3D reconstruction models: query tokens encode view-specific geometric requests and are sensitive to compression, while key-value tokens represent shared scene context and tolerate aggressive compression. Guided by this insight, we propose Spark3R, a training-free acceleration framework that decouples the compression of query tokens and key-value tokens by assigning distinct reduction factors, with intra-group token merging applied to query tokens and lightweight token pruning to key-value tokens. Additionally, Spark3R adaptively adjusts the key-value reduction factor across layers, further improving the quality-efficiency trade-off. As a plug-and-play framework requiring no retraining, Spark3R integrates directly into multiple pretrained feed-forward 3D reconstruction models, including VGGT, π^3, Depth-Anything-3, and VGGT-Ω, and achieves up to 28times speedup on 1,000-frame inputs while maintaining competitive reconstruction quality.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.06270
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.06270 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/2605.06270 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/2605.06270 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.