Scene Parameter Saliency via Differentiable Light Transport

Gradient-based saliency methods reveal which input features most influence a neural network's output, and are a standard tool for model interpretability.

Gradient-based saliency methods reveal which input features most influence a neural network's output, and are a standard tool for model interpretability. We observe that differentiable renderers, which are conventionally used for parameter optimisation, produce an analogous form…