A Latent Space Diffusion Transformer for High-Quality Video Frame Interpolation

Abstract excerpt

Video Frame Interpolation (VFI) is critical for generating smooth slow-motion and increasing video frame rates, yet it faces significant challenges in achieving high fidelity, accurate motion modeling, and robust spatiotemporal consistency, particularly for large displacements and occlusions. This paper introduces TemporalFlowDiffuser (TFD), a novel end-to-end latent space diffusion Transformer designed to overcom...

Topics

Open a Topic to create a Post that cites this publication.

• Algorithms
• Deep Learning
• Image Enhancement
• Image Processing, Computer-Assisted
• Phenotype
• Retina

Identifiers and source

Literature Corpus work

94451b04-2572-50e8-b734-b797f258acd8

DOI

10.20944/preprints202512.1587.v1