Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

raw image reconstruction

Raw image reconstruction is a computational imaging and compression process that recovers original, high-fidelity camera sensor data from standard processed images, such as sRGB or JPEG formats, often with the assistance of compact metadata. When a digital camera captures an image, its image signal processor converts raw sensor measurements into standard formats through a sequence of non-linear and lossy steps, including demosaicing, color space transformations, tone mapping, and compression, which discard radiometric linearity, dynamic range, and high-bit-depth information. Raw image reconstruction algorithms model and invert these transformations or decode compressed sensor signals using standard image previews as guidance, restoring the original linear sensor responses and spectral characteristics to facilitate precise photographic post-processing, radiometric analysis, and downstream computer vision tasks without requiring excessive file storage.

1 item

MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction

MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction

Peize Li, Fanhu Zeng, Tongda Xu, Xingguo Xu, Xinjie Zhang, Xingtong Ge, Haotian Zhang, Yan Wang

OrganizationsDalian University of TechnologyKing's College LondonMicrosoftPeking UniversityThe Hong Kong University of Science and TechnologyTsinghua University

Why you should read this

Presents MambaRaw, a selective state space framework that replaces quadratic attention with tiled scanning to reconstruct 4K raw images from embedded JPEG previews with improved fidelity and reduced coding latency.

In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can exploit this side information when recovering raw images, their context models often become computationally expensive especially at high resolution, eg, 4K raw image, given that attention mechanisms scale quadratically with feature maps, hindering its practical application. To address these limitations, we propose MambaRaw, a JPEG-conditioned metadata-based raw image reconstruction framework that uses State Space Models (SSMs) to estimate entropy parameters efficiently. Our key contribution comprises a Spatial-Energy Coupled Context Modeling mechanism with two lightweight modules: (1) TileMambaBlock, which performs Mamba-style selective scanning only on information-dense tiles to improve the efficiency; and (2) Energy-Aware Refinement (EAR), an identity-initialized residual module that enhance feature representation to match the long-tail energy distribution of raw signals. Extensive experiments on three camera datasets (Sony, Olympus, Samsung) show consistent improvements over strong metadata-based baselines and set a new state of the art for JPEG-guided raw reconstruction with great efficiency. Notably, at low metadata bitrates, MambaRaw increases PSNR by 1.2--1.4 dB and reduces end-to-end coding latency by about 9%. Code is released at this https URL.

Added

2026-09-29