Recurrent Dynamic Range Extension

2026-09-11

AI Summary

该研究通过递归执行网络逐步扩展图像的动态范围，使用记忆回放减少重建误差，从而解决复杂场景中高动态范围图像的重建问题。

Abstract

We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.

Problem

• Recurrent Dynamic Range Extension
• HDR
• exposure value
• dynamic range
• RAW images

Innovation

• Recurrent Dynamic Range Extension
• Memory Replay
• Adversarial Losses
• RAW Images
• HDR Reconstruction