Abstract Inverse tone mapping technique is widely used to restore the lost textures from a single low dynamic range image. Recently, many stack‐based deep inverse tone mapping networks have achieved impressive results by estimating a set of multi‐exposure images from a single low dynamic range input. However, there are still some limitations. On the one hand, these methods usually set a fixed length for the estimated multi‐exposure stack, which may introduce computational redundancy or cause inaccurate results. On the other hand, they neglect that the difficulties of estimating each exposure value are different and use the identical model to increase or decrease exposure value. To solve these problems, the authors design an exposure decision network to adaptively determine the number of times the exposure of low dynamic range input should be increased or decreased. Meanwhile, the authors decouple the increasing/decreasing process into two sub‐modules, exposure adjustment and optional detail recovery, based on the characteristics of different variations of exposure values. With these improvements, this method can fast and flexibly estimate the multi‐exposure stack from a single low dynamic range image. Experiments on several datasets demonstrate the advantages of the proposed method compared to state‐of‐the‐art inverse tone mapping methods.