SOURCE-LINKED INTELLIGENCE

ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth zoom (DCSZ) methods attempt to mitigate this by fine-tuning frame interpolation (FI) models on DCSZ data, they struggle with the large cross-view disparities and complex geometric transformations. Considering that the generative prior of diffusion models is suitable for addressing this problem, we explore their application to DCSZ. However, naively applying existing diffusion-based FI models stil

Read original source ↗ Open in workspace

recordType

paper

region

Global