Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910189556334592 |
|---|---|
| author | Javadi, Amirhosein Bidokhti, Shirin Saeedi Javidi, Tara |
| author_facet | Javadi, Amirhosein Bidokhti, Shirin Saeedi Javidi, Tara |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02849 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion Javadi, Amirhosein Bidokhti, Shirin Saeedi Javidi, Tara Computer Vision and Pattern Recognition 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. |
| title | Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02849 |