by America Ortiz | Oct 2, 2023 | Capture, Visual Computing
ReNeRF: Relightable Neural Radiance Fields with Nearfield Lighting In this paper, we target the application scenario of capturing high-fidelity assets for neural relighting in controlled studio conditions, but without requiring a dense light stage. Instead, we...
by America Ortiz | Aug 31, 2023 | Machine Learning
The Score-Difference Flow for Implicit Generative Modeling The SD flow defines an optimal path between arbitrary probability distributions and also provides a theoretical link between model classes that individually address the three challenges of the generative...