Search papers, labs, and topics across Lattice.
The paper introduces DOME-HDR, a dual-output framework for high dynamic range (HDR) reconstruction that generates both a perceptually balanced standard dynamic range (SDR) image and a consistent HDR image using gain map inverse tone mapping. By leveraging a LoRA-adapted latent diffusion model and a dual cross-attention fusion module, the method effectively synthesizes an SDR from three bracketed low dynamic range (LDR) inputs while maintaining stability through mid-exposure anchoring. Evaluations on multiple benchmark datasets demonstrate that DOME-HDR achieves state-of-the-art HDR reconstruction quality, with ablation studies highlighting the contributions of its architectural components.
Achieving state-of-the-art HDR reconstruction quality, DOME-HDR reveals how dual-output synthesis can enhance both SDR and HDR imaging from bracketed inputs.
We propose DOME-HDR, a dual-output multi-exposure HDR reconstruction framework that jointly produces a perceptually balanced SDR image and a consistent HDR image via gain map inverse tone mapping. Given three bracketed LDR inputs, DOME-HDR first synthesizes a base SDR using a LoRA-adapted latent diffusion model. A dual cross-attention fusion module injects complementary structural and color cues from the under- and over-exposed images while anchoring on the mid exposure for stability. The synthesized SDR then guides HPGM, our HDR Prior-guided Gain Map network, to predict a spatially varying gain map for reliable dynamic-range expansion. We evaluate on Kalantari, Tel, and Challenge123 using both full-reference and no-reference metrics, where DOME-HDR achieves state-of-the-art HDR reconstruction quality; ablations further confirm the effectiveness of dual cross-attention and SDR-guided gain map estimation.
