Lucky High Dynamic Range Smartphone Imaging

• URL: http://arxiv.org/abs/2604.19976v1
• Date: Tue, 21 Apr 2026 20:35:36 GMT
• Title: Lucky High Dynamic Range Smartphone Imaging
• Abstract summary: This paper proposes an approach that robustly captures dynamic range using a handheld smartphone camera and lightweight networks.<n>We validate our system on both synthetic imagery and unseen real bracketed images.<n>Our training process relies only on synthetic captures yet generalizes to unseen real photos from several cameras.
• Score: 36.89557177931477
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite decades of research. A variety of high dynamic range (HDR) image capture and processing techniques have been proposed, and, in practice, they can extend the dynamic range by 3-5 stops for handheld photography. This paper proposes an approach that robustly captures dynamic range using a handheld smartphone camera and lightweight networks suitable for running on mobile devices. Our method operates indirectly on linear raw pixels in bracketed exposures. Every pixel in the final HDR image is a convex combination of input pixels in the neighborhood, adjusted for exposure, and thus avoids hallucination artifacts typical of recent deep image synthesis networks. We validate our system on both synthetic imagery and unseen real bracketed images -- we confirm zero-shot generalization of the method to smartphone camera captures. Our iterative inference architecture is capable of processing an arbitrary number of bracketed input photos, and we show examples from capture stacks containing 3--9 images. Our training process relies only on synthetic captures yet generalizes to unseen real photos from several cameras. Moreover, we show that this training scheme improves other SOTA methods over their pretrained counterparts.

Related papers

• AIM 2025 Challenge on Real-World RAW Image Denoising [58.132121871352474]
  The AIM 2025 Real-World RAW Image Denoising Challenge aims to advance efficient and effective denoising techniques grounded in data synthesis.<n>The competition is built upon a newly established evaluation benchmark featuring challenging low-light noisy images captured in the wild using five different DSLR cameras.<n>By pushing the boundaries of camera-agnostic low-light RAW image denoising trained on synthetic data, the competition promotes the development of robust and practical models.
  arXiv  Detail & Related papers  (2025-10-08T03:22:42Z)
• Neural Field Representations of Mobile Computational Photography [4.459996749171579]
  I show how carefully designed neural field models can compactly represent complex geometry and lighting effects.<n>I enable applications such as depth estimation, layer separation, and image stitching directly from collected in-the-wild mobile photography data.
  arXiv  Detail & Related papers  (2025-08-08T00:03:46Z)
• MobileMEF: Fast and Efficient Method for Multi-Exposure Fusion [0.6261722394141346]
  We propose a new method for multi-exposure fusion based on an encoder-decoder deep learning architecture. Our model is capable of processing 4K resolution images in less than 2 seconds on mid-range smartphones.
  arXiv  Detail & Related papers  (2024-08-15T05:03:14Z)
• Deep Hybrid Camera Deblurring for Smartphone Cameras [18.053081461607544]
  We propose a learning-based deblurring framework for smartphones. We capture a long-exposure wide image and short-exposure burst ultra-wide images, and utilize the burst images to deblur the wide image. Our experiments demonstrate that HCDeblur achieves state-of-the-art deblurring quality.
  arXiv  Detail & Related papers  (2023-12-20T11:02:59Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography [54.36608424943729]
  We show that in a ''long-burst'', forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. We devise a test-time optimization approach that fits a neural RGB-D representation to long-burst data and simultaneously estimates scene depth and camera motion.
  arXiv  Detail & Related papers  (2022-12-22T18:54:34Z)
• Perceptual Image Enhancement for Smartphone Real-Time Applications [60.45737626529091]
  We propose LPIENet, a lightweight network for perceptual image enhancement. Our model can deal with noise artifacts, diffraction artifacts, blur, and HDR overexposure. Our model can process 2K resolution images under 1 second in mid-level commercial smartphones.
  arXiv  Detail & Related papers  (2022-10-24T19:16:33Z)
• High Dynamic Range and Super-Resolution from Raw Image Bursts [52.341483902624006]
  This paper introduces the first approach to reconstruct high-resolution, high-dynamic range color images from raw photographic bursts captured by a handheld camera with exposure bracketing. The proposed algorithm is fast, with low memory requirements compared to state-of-the-art learning-based approaches to image restoration. Experiments demonstrate its excellent performance with super-resolution factors of up to $times 4$ on real photographs taken in the wild with hand-held cameras.
  arXiv  Detail & Related papers  (2022-07-29T13:31:28Z)
• Mesoscopic photogrammetry with an unstabilized phone camera [8.210210271599134]
  We present a feature-free photogrammetric computation technique that enables quantitative 3D mesoscopic (mm-scale height variation) imaging. Our end-to-end, pixel-intensity-based approach jointly registers and stitches all the images by estimating a coaligned height map. We also propose strategies for reducing time and memory, applicable to other multi-frame registration problems.
  arXiv  Detail & Related papers  (2020-12-11T00:09:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.