cs.CVNov 17, 2026

CueSplat: Learning to Schedule Sparse Deformation for Dynamic Gaussian Splatting on Edge Devices

Authors: Qingyuan Tang, He Zhu, Shixuan Sun, Anbang Wu, Jingwen Leng, Minyi Guo, Yu Feng

Organizations: Shanghai Jiaotong University

Abstract

Deformation-based 4D Gaussian splatting (4DGS) enables dynamic scene rendering. However, evaluating deformation networks for all Gaussians at every frame is compute-intensive on edge devices. We find that Gaussian trajectories are often locally predictable, yet prediction reliability varies across Gaussians and time. Thus, we propose CueSplat, a post-training framework that exploits local temporal regularity while keeping the pretrained backbone frozen and retaining its Gaussian set. Specifically, CueSplat predicts Gaussian attributes from recent history and uses a lightweight learned router to select exact deformation updates within a scene-specific budget calibrated offline. Selection accounts for prediction reliability and rendering contribution. Selected indices are reused across nearby frames to reduce routing overhead, while selected Gaussians still receive exact updates each frame. To control accumulated prediction error, we use drift signals to schedule three consecutive full-deformation frames that rebuild the prediction history. Evaluated across four mainstream 4DGS algorithms, CueSplat achieves up to 6.74×6.74\times and 8.15×8.15\times speedups on Jetson AGX Orin and Orin NX, respectively, with a negligible quality drop (at most 0.160.16 dB in dataset-average PSNR).

Figures & tables

Explore similar work

CardsList
  1. Implicit 4D Gaussian Splatting for Fast Motion with Large Inter-Frame Displacements

    Jul 14, 2026Seung-gyeom Kim, Areum Kim, Yongjae Yoo +13D Gaussian Splatting4D Reconstruction

  2. TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting

    Apr 1, 2026Suwoong Yeom, Joonsik Nam, Seunggyu Choi +74D ReconstructionDynamic Scene Reconstruction