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. We observe that differentiable renderers, which are conventionally used for parameter optimisation, produce an analogous form of saliency: given any scalar metric evaluated on a rendered image, a single reverse-mode differentiation pass yields per-parameter gradients that identify which scene elements most influence the metric. We call these gradient fields metric saliency maps. Unlike neural saliency, which propagates attribution through lea
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%HKUDS/LightRAG →
“Fuzzy title match (0.94): “Scene Parameter Saliency via Differentiable Light Transport” ≈ “HKUDS/LightRAG””
- FuzzySimilar title/name (fuzzy) · 87%lightgbm-org/LightGBM →
“Fuzzy title match (0.94): “Scene Parameter Saliency via Differentiable Light Transport” ≈ “lightgbm-org/LightGBM””
- LinkedLinked via arxiv author · 85%Linas Beresna →
“Scene Parameter Saliency via Differentiable Light Transport”
- LinkedLinked via arxiv author · 85%Eugene Fiume →
“Scene Parameter Saliency via Differentiable Light Transport”