aiqbench analysis
This research introduces an image-conditional diffusion transformer (ICDT) that replaces the standard U-Net backbone in denoising diffusion models to enhance degraded underwater imagery. By leveraging transformer scalability and a hybrid loss function, the method achieves state-of-the-art quality while significantly accelerating the sampling process compared to prior generative approaches. The work represents a notable advancement in applying large-scale generative architectures to specialized computer vision tasks within the AI domain.
Image-Conditional Diffusion Transformer for Underwater Image Enhancement
arXiv:2407.05389v2 Announce Type: replace-cross Abstract: Underwater image enhancement (UIE) has attracted much attention owing to its importance for underwater operation and marine engineering. Motivated by the recent advance in generative models, we propose a novel UIE method based on image-conditional diffusion transformer (ICDT). Our method takes the degraded underwater image as the conditional input and converts it into latent space where ICDT is applied. ICDT replaces the conventional U-Net backbone in a denoising diffusion probabilistic model (DDPM) with a transformer, and thus inherits favorable properties such as scalability from transformers. Furthermore, we train ICDT with a hybrid loss function involving variances to achieve better log-likelihoods, which meanwhile significantly accelerates the sampling process. We experimentally assess the scalability of ICDTs and compare with prior works in UIE on the Underwater ImageNet dataset. Besides good scaling properties, our largest model, ICDT-XL/2, outperforms all comparison methods, achieving state-of-the-art (SOTA) quality of image enhancement.
Abstract:Underwater image enhancement (UIE) has attracted much attention owing to its importance for underwater operation and marine engineering. Motivated by the recent advance in generative models, we propose a novel UIE method based on image-conditional diffusion transformer (ICDT). Our method takes the degraded underwater image as the conditional input and converts it into latent space where ICDT is applied. ICDT replaces the conventional U-Net backbone in a denoising diffusion probabilistic model (DDPM) with a transformer, and thus inherits favorable properties such as scalability from transformers. Furthermore, we train ICDT with a hybrid loss function involving variances to achieve better log-likelihoods, which meanwhile significantly accelerates the sampling process. We experimentally assess the scalability of ICDTs and compare with prior works in UIE on the Underwater ImageNet dataset. Besides good scaling properties, our largest model, ICDT-XL/2, outperforms all comparison methods, achieving state-of-the-art (SOTA) quality of image enhancement.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2407.05389 [cs.CV]
(or arXiv:2407.05389v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2407.05389 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 243 words
Related coverage
Quantum nanoparticles mix frequencies to cut imaging noise
Quantum Zeitgeist · Sep 7, 2026
Triton-Based Optimization of Video Sparse Attention on ROCm
AMD · Jul 13, 2026
Efficient Fairness Auditing Across Guidance Scales in Text-to-Image Diffusion Models via Causal Abstraction
arXiv · Sep 10, 2026
Best Free Image Generators on Hugging Face Right Now!
KDnuggets · Jun 9, 2026