Pith. sign in

REVIEW 3 cited by

SPIRE: Semantic Prompt-Driven Image Restoration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.11595 v2 pith:A3MX3HG7 submitted 2023-12-18 cs.CV

classification cs.CV
keywords restorationimagesemanticspirecontrolfine-levelfirstframework
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text-driven diffusion models have become increasingly popular for various image editing tasks, including inpainting, stylization, and object replacement. However, it still remains an open research problem to adopt this language-vision paradigm for more fine-level image processing tasks, such as denoising, super-resolution, deblurring, and compression artifact removal. In this paper, we develop SPIRE, a Semantic and restoration Prompt-driven Image Restoration framework that leverages natural language as a user-friendly interface to control the image restoration process. We consider the capacity of prompt information in two dimensions. First, we use content-related prompts to enhance the semantic alignment, effectively alleviating identity ambiguity in the restoration outcomes. Second, our approach is the first framework that supports fine-level instruction through language-based quantitative specification of the restoration strength, without the need for explicit task-specific design. In addition, we introduce a novel fusion mechanism that augments the existing ControlNet architecture by learning to rescale the generative prior, thereby achieving better restoration fidelity. Our extensive experiments demonstrate the superior restoration performance of SPIRE compared to the state of the arts, alongside offering the flexibility of text-based control over the restoration effects.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance

    cs.CV 2025-05 conditional novelty 6.0 of 10

    TextSR super-resolves multilingual scene text by conditioning a diffusion model on UTF-8-encoded OCR characters, achieving top OCR accuracy on TextZoom and on small/medium text in a self-defined TextVQA evaluation.

  2. TASR: Timestep-Aware Diffusion Model for Image Super-Resolution

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A timestep-aware adapter that weights ControlNet guidance early and pretrained diffusion features late improves no-reference perceptual quality in image super-resolution.

  3. Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration

    cs.CV 2025-04 conditional novelty 4.0 of 10

    A 0.4B adapter with squeeze-and-excitation layers lets the frozen 12B Flux model restore images after training on 350k Flux-generated images, at roughly one-tenth of the training cost of prior generative restoration systems.

Pith tools