← Back to all news
arXiv Computer Vision

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

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.

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 →
arXiv Computer Vision
Sep 11

InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction

InstantHDR is a feed-forward network that initializes high dynamic range (HDR) 3D scenes from uncalibrated multi-exposure low dynamic range (LDR) image collections in a single forward pass. It uses geometry-guided appearance modeling for multi-exposure fusion and a meta-network for scene-specific tone mapping. The authors also created a pre-training dataset, HDR-Pretrain, with 168 Blender-rendered scenes to support generalizable HDR models, achieving a speedup of about 700× over state‑of‑the‑art optimization methods while maintaining comparable quality after lightweight post‑optimization.

By Dingqiang Ye, Jiacong Xu, Jianglu Ping, Yuxiang Guo, Chao Fan, Vishal M. Patel
benchmarks
More like this →
arXiv Computer Vision
Sep 4

Generating HDR Video from SDR Video

The paper presents a framework for converting standard dynamic range (SDR) videos into high dynamic range (HDR) videos using large-scale generative video models. It introduces a Multi-Exposure Video Model (MEVM) that predicts exposure-bracketed linear SDR sequences from a single nonlinear SDR input, and a Video Merging Model (VMM) that fuses these predictions into a high-quality HDR sequence while preserving detail in shadows and highlights. Experiments, qualitative evaluation, and a user study demonstrate robust HDR conversion for casual consumer footage and iconic films, and the approach can be integrated into existing SDR generative video pipelines.

By SaiKiran Tedla, Francesco Banterle, Trevor Canham, Karanpreet Raja, David B. Lindell, Kiriakos N. Kutulakos, Jiacheng Li, Feiran Li, Daisuke Iso
More like this →