by America Ortiz | Oct 2, 2023 | Machine Learning
Controllable Inversion of Black-Box Face Recognition Models via Diffusion We tackle the challenging task of inverting the latent space of pre-trained face recognition models without full model access (i.e. black-box setting). Our method, the identity denoising...
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 Melanie Cadalbert | Jul 23, 2023 | Rendering, Video Processing, Visual Computing
Kernel-Based Frame Interpolation for Spatio-TemporallyAdaptive Rendering We propose a frame interpolation method for rendered content with two key features. First, a kernel based frame synthesis model which predicts the interpolated frame as a linear mapping of the...
by Melanie Cadalbert | Jun 26, 2023 | Rendering, Video Processing, Visual Computing
Deep Compositional Denoising on Frame Sequences Path tracing is the prevalent rendering algorithm in the animated movies and visual effects industry, thanks to its simplicity and ability to render physically plausible lighting effects. However, we must simulate...
by Melanie Cadalbert | Jun 4, 2023 | Rendering, Video Processing, Visual Computing
Continuous Landmark Detection with 3D Queries We propose the first facial landmark detection network that can predict continuous, unlimited landmarks, allowing to specify the number and location of the desired landmarks at inference time. Our method combines a simple...
