Intrinsic image decomposition using physics-based cues and CNNs

作者：

Highlights：

• A (generalised) physics-based cue to steer a CNN model by an integrated IID pipeline is proposed.

• Reflectance cues are exploited for shading computation through a stacked approach.

• Separating the intrinsic components for the learning phase is shown to be beneficial.

• Proposed method has generalization capacity to unseen domains & can cope with dataset bias problem.

摘要

•A (generalised) physics-based cue to steer a CNN model by an integrated IID pipeline is proposed.•Reflectance cues are exploited for shading computation through a stacked approach.•Separating the intrinsic components for the learning phase is shown to be beneficial.•Proposed method has generalization capacity to unseen domains & can cope with dataset bias problem.

论文关键词：Computer vision,Physics based vision,Intrinsics image decomposition,Deep learning

论文评审过程：Received 11 August 2021, Revised 8 June 2022, Accepted 16 August 2022, Available online 23 August 2022, Version of Record 5 September 2022.

论文官网地址：https://doi.org/10.1016/j.cviu.2022.103538