3260 papers • 126 benchmarks • 313 datasets
SVE-based HDR imaging, also known as single-shot HDR imaging, algorithms capture a scene with pixel-wise varying exposures in a single image and then computationally synthesize an HDR image, which benefits from the multiple exposures of the single image.
(Image credit: Papersgraph)
These leaderboards are used to track progress in single-shot-hdr-reconstruction-1
No benchmarks available.
Use these libraries to find single-shot-hdr-reconstruction-1 models and implementations
No subtasks available.
A novel single-shot high dynamic range (HDR) imaging algorithm based on exposure-aware dynamic weighted learning, which reconstructs an HDR image from a spatially varying exposure (SVE) raw image by developing a network that learns local dynamic filters to exploit local neighboring pixels across color channels.
A method to explicitly estimate the tone mapping function and its corresponding HDR image in one network and generalizes well under different tone-mapping functions and achieves SOTA performance is proposed.
Adding a benchmark result helps the community track progress.