← Back to all news
arXiv Computer Vision By Zhengguo Li, Chaobing Zheng, Wei Wang

Neural Block-wise Auto-exposure for Single-Shot High Dynamic Range Imaging

Read the original on arXiv Computer Vision →

The paper proposes a neural block-wise auto‑exposure algorithm for single‑shot high dynamic range imaging that predicts exposure times for non‑overlapping 16×16 image blocks. It uses a temporary image—either sRGB or raw—to guide the exposure mapping, noting that raw images provide better radiance measurement and thus more accurate exposure decisions, especially in highlight and shadow regions. Experimental results confirm the effectiveness of the approach in reducing artifacts and preserving detail.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 28

Physics Guided Diffusion Model Based Exposure Interpolation for High Dynamic Range Imaging

The paper introduces a physics-guided diffusion model for exposure interpolation in high dynamic range imaging, aiming to eliminate brightness order reversal artifacts that arise when fusing two large-exposure-ratio SDR images. The method first interpolates an initial image using a physics-driven component, then refines high-frequency details with a diffusion model that leverages correlation analysis to reduce noise-target variation and fitting error amplification. Experiments demonstrate that this approach outperforms existing convolutional neural network-based exposure interpolation algorithms by generating richer high-frequency content.

By Zhengguo Li, Chaobing Zheng
diffusion
More like this →
arXiv Computer Vision
Sep 14

Recurrent Dynamic Range Extension

The paper introduces a method for progressively extending the dynamic range of an image by learning to increase it by a single exposure value first, then applying the network recurrently to achieve full HDR reconstruction. The approach is agnostic to input dynamic range, targets a bounded output domain, and utilizes RAW images with adversarial losses to produce realistic results. Memory Replay during backpropagation allows training over multiple inference stages, reducing reconstruction errors and enabling robust recovery of bright highlights in long‑tailed HDR scenes.

By Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh, Ya\u{g}{\i}z Aksoy
safety
More like this →