Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate

The paper proposes that super‑resolution should be performed in a latent space that is close to the manifold of high‑resolution images, rather than in reconstruction‑oriented or pixel spaces. By using the latent space of 23 fused layers of a frozen DINOv3‑L model, degraded images are embedded near this manifold, enabling a 415M decoder (RAESR) to map them back and decode to pixels in a single pass. RAESR achieves the best fidelity–perception trade‑off on several benchmarks while running at 37 ms per 512×512 image on a single H20 GPU, outperforming models that use a VAE latent substrate.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• rag
• diffusion
• benchmarks
• safety