InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction
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 initializes 3D HDR scenes from uncalibrated multi-exposure LDR collections in a fast single forward pass. Specifically, we design a geometry-guided appearance modeling for multi-exposure fusion, and a meta-network for generalizable scene-specific ton...
| Authors | Dingqiang Ye, Jiacong Xu, Jianglu Ping et al. |
|---|---|
| Primary category | cs.CV |
| Published | 11 March 2026 |
| Last updated at source | 9 September 2026 |
Models and datasets referencing this paper
- Bugjudger/HDR_PretrainDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.