Metraipolis › archive › dc_ffadf6b36604

PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution — arXiv:2609.30988

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30988
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:38.690Z
SHA-256 of the archived text
fba9e338a0723ee09cac0772ba05a8764badcc6c3204b08bbe7ebcf3cba0ab27
Stable URL of this page
https://metraipolis.com/documento/dc_ffadf6b36604

How to cite

PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution — arXiv:2609.30988 — arXiv (en), https://arxiv.org/abs/2609.30988 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffadf6b36604 (Metraipolis archive dc_ffadf6b36604, sha256 fba9e338a0723ee09cac0772ba05a8764badcc6c3204b08bbe7ebcf3cba0ab27)
BibTeX
@misc{dcffadf6b36604,
  title = {PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution — arXiv:2609.30988},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30988},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffadf6b36604; sha256 fba9e338a0723ee09cac0772ba05a8764badcc6c3204b08bbe7ebcf3cba0ab27},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30988. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while preserving faithful content. Diffusion-based SR benefits from strong generative priors but incurs substantial computational overhead, whereas feed-forward CNN and Transformer SR models are efficient yet often struggle to recover realistic high-frequency details. This motivates a natural question: can diffusion priors be transferred to existing diffusion-free SR networks without introducing diffusion components at inference time? To this end, we propose PhoenixSR, a generative heterogeneous distillation framework that transfers diffusion priors to independently designed feed-forward SR networks through score-based distribution matching. Rather than aligning heterogeneous features or imitating sampled diffusion outputs, PhoenixSR uses the pretrained diffusion model as distribution-level supervision, while paired SR supervision preserves reconstruction fidelity. To make distribution matching effective for fidelity-sensitive SR, we introduce Heterogeneous Distribution Adaptation, which adapts the target score to the SR domain, improves tracking of the evolving student distribution, and anchors training with paired supervision. We further employ Directional Reliability Weighting, a lightweight residual-consistency-based reweighting strategy that reduces unstable distributional guidance. All diffusion-related components are removed after training, leaving the original student architecture and inference cost unchanged. Experiments on three SR benchmarks and six feed-forward backbones, including SwinIR, HAT, Real-ESRGAN, and SeeMoRe, show consistent perceptual improvements with largely preserved reconstruction fidelity.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30988 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T02:50:19.069Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).