Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion

TL;DR

This paper introduces ActDiff-VC, a diffusion-based video compression method that uses sparse conditioning signals for ultra-low-bitrate, perceptually realistic video reconstruction, outperforming existing codecs in rate-distortion trade-offs.

Contribution

The work presents a novel diffusion-based framework with content-adaptive keyframe and trajectory selection for ultra-low-bitrate video compression.

Findings

Achieves up to 64.6% bitrate reduction at matched NIQE.

Improves KID and FID scores significantly at comparable bitrates.

Provides favorable perceptual rate--distortion trade-offs in experiments.

Abstract

Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work, we present ActDiff-VC, a diffusion-based video compression framework for the ultra-low-bitrate regime. Our method partitions videos into variable-length segments, transmits keyframes only when needed, and summarizes temporal dynamics using a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder synthesizes the remaining frames, enabling perceptually realistic reconstruction under severe rate constraints. To support this design, we introduce two mechanisms: content-adaptive keyframe selection and budget-aware sparse trajectory selection, which together enable compact yet effective conditioning for generative reconstruction. Experiments on the UVG and MCL-JCV benchmarks show that ActDiff-VC achieves up to 64.6\% bitrate reduction at matched NIQE, improves KID by up to 64.6\% and FID by up to 37.7\% at comparable bitrates against strong learned codecs, and delivers favorable perceptual rate--distortion trade-offs relative to learned and diffusion-based baselines in the ultra-low-bitrate regime.