mlsanityData to 7 Oct 2026

Sparse Video Representation Using Steered Mixture-of-Experts With Global Motion Compensation

arXiv 2209.05993 ↗First posted 13 Sep 2022eess.IVcited by 2

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Steered-Mixtures-of Experts (SMoE) present a unified framework for sparse representation and compression of image data with arbitrary dimensionality. Recent work has shown great improvements in the performance of such models for image and light-field representation. However, for the case of videos the straight-forward application yields limited success as the SMoE framework leads to a piece-wise linear representation of the underlying imagery which is disrupted by nonlinear motion. We incorporate a global motion model into the SMoE framework which allows for higher temporal steering of the kernels. This drastically increases its capabilities to exploit correlations between adjacent frames by only adding 2 to 8 motion parameters per frame to the model but decreasing the required amount of kernels on average by 54.25%, respectively, while maintaining the same reconstruction quality yielding higher compression gains.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 2 of its 16 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

2 of 16 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Edge-Aware Autoencoder Design for Real-Time Mixture-of-Experts Image Compression25 Jul

Other references · 1

  1. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Adaptive Segmentation-Based Initialization for Steered Mixture of Experts Image Regressioncited by 3
  2. 2025Rasterized Steered Mixture of Experts for Efficient 2D Image Regressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Steered Mixture-of-Experts Autoencoder Design for Real-Time Image Modelling and Denoising
  2. 2026Edge-Aligned Initialization of Kernels for Steered Mixture-of-Experts
  3. 2023Steered Mixture of Experts Regression for Image Denoising with Multi-Model-Inference
  4. 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
  5. 2024On the Role of Discrete Representation in Sparse Mixture of Experts
  6. 2024MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
  7. 2026VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer
  8. 2025Mixture of Group Experts for Learning Invariant Representations