BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors

2026-04-25

AI Summary

This work addresses the limitations of existing burst image super-resolution methods, which often produce over-smoothed results in complex texture regions and fail to effectively leverage pretrained generative priors. To overcome these issues, the authors propose BurstGP, a novel diffusion-based approach that innovatively integrates video-level sRGB generative priors with raw burst inputs. The method introduces a degradation-aware conditioning mechanism and a robust sRGB-to-linear RGB inverse transformation module, further enhanced by multi-frame alignment cues to improve fine detail synthesis. BurstGP achieves significantly sharper textures and structures while preserving high fidelity, outperforming state-of-the-art methods on perceptual metrics such as MUSIQ and LPIPS, thereby enabling more photorealistic super-resolution reconstruction.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) frames, relying on temporal redundancy and spatial coherence across the burst. While conventional methods achieve impressive results, they often struggle with complex textures and oversmoothing. Diffusion models, particularly those pretrained on high-quality data, have shown remarkable capability in generating realistic details for image and video super-resolution. However, their potential remains largely under-explored in BISR, where existing approaches typically rely on task-specific diffusion models trained from scratch and operate on single-frame reconstructions. In this work, we propose BurstGP, a novel diffusion-based solution for BISR, which leverages generative priors of recent foundation models to overcome these issues. In particular, we build a multiframe-aware diffusion model on top of a conventional BISR approach, which boosts image quality with minimal loss to fidelity. Further, we introduce (i) a novel degradation-aware conditioning mechanism, which controls synthesis of fine details based on the estimated degradation in the input, and (ii) a robust sRGB-to-lRGB inverter, enabling us to utilize generative multiframe (video) sRGB priors, while operating with raw input and lRGB output images. Empirically, we demonstrate that BurstGP outperforms the existing state of the art, both quantitatively (especially with respect to perceptual metrics, including MUSIQ and LPIPS) and qualitatively. In particular, our proposed method excels at recovering richer textures and finer structural details, highlighting the potential of video priors for BISR over traditional methods.

Problem

• Burst Image Super Resolution
• Generative Priors
• Diffusion Models
• Texture Recovery
• Over-smoothing

Innovation

• Burst Image Super-Resolution
• Diffusion Models
• Generative Priors
• Degradation-Aware Conditioning
• sRGB-to-lRGB Inversion