AI & ML Efficiency Breakthrough

InstantHDR achieves high-quality 3D HDR reconstruction 700x faster than current optimization-based methods.

arXiv · March 13, 2026 · 2603.11298

Dingqiang Ye, Jiacong Xu, Jianglu Ping, Yuxiang Guo, Chao Fan, Vishal M. Patel

Why it matters

By moving from per-scene optimization to a feed-forward network with a specialized meta-network for tone mapping, it enables near-instant HDR novel view synthesis. This is a massive leap for real-time digital twin and AR/VR applications.

From the abstract

High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes from multi-exposure low dynamic range (LDR) images. Existing HDR pipelines heavily rely on known camera poses, well-initialized dense point clouds, and time-consuming per-scene optimization. Current feed-forward alternatives overlook the HDR problem by assuming exposure-invariant appearance. To bridge this gap, we propose InstantHDR, a feed-forward network that reconstructs 3D HDR scenes from uncalibrated multi-ex