$\text{F}^2\text{HDR}$: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
This addresses the challenge of HDR video reconstruction for applications like photography and video processing, but it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of reconstructing High Dynamic Range (HDR) videos from alternating-exposure Low Dynamic Range (LDR) frames in dynamic scenes, achieving state-of-the-art performance on real-world benchmarks with ghost-free and high-fidelity results.
Reconstructing High Dynamic Range (HDR) videos from sequences of alternating-exposure Low Dynamic Range (LDR) frames remains highly challenging, especially under dynamic scenes where cross-exposure inconsistencies and complex motion make inter-frame alignment difficult, leading to ghosting and detail loss. Existing methods often suffer from inaccurate alignment, suboptimal feature aggregation, and degraded reconstruction quality in motion-dominated regions. To address these challenges, we propose $\text{F}^2\text{HDR}$, a two-stage HDR video reconstruction framework that robustly perceives inter-frame motion and restores fine details in complex dynamic scenarios. The proposed framework integrates a flow adapter that adapts generic optical flow for robust cross-exposure alignment, a physical motion modeling to identify salient motion regions, and a motion-aware refinement network that aggregates complementary information while removing ghosting and noise. Extensive experiments demonstrate that $\text{F}^2\text{HDR}$ achieves state-of-the-art performance on real-world HDR video benchmarks, producing ghost-free and high-fidelity results under large motion and exposure variations.