3 papers
cs.GR2026
Constant-Memory Differentiable Light Tracing
Linas Beresna, Eugene Fiume
Reverse-mode differentiation of Monte Carlo light transport naively requires storing a computation graph whose size grows with path length, making it impractical for deep or high-s…
cs.CV2026
Scene Parameter Saliency via Differentiable Light Transport
Linas Beresna, Eugene Fiume
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 differenti…
cs.GR2026
Glare Mitigation using a Differentiable Unified Glare Rating
Linas Beresna, Eugene Fiume
Recent research in differentiable light transport extends the utility of computer graphics algorithms beyond traditional image generation, offering powerful tools for physical inve…