This is the official repository for our ICCV 2023 paper Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis.

Abstract: Unpaired shape-to-shape translation refers to the task of transforming the geometry and semantics of an input shape into a new shape domain without paired training data. Previous methods ...

The heavy metal titans have announced an epic show at the Hertfordshire estate next year. Find out who’s joining them as support acts, how to get there and if you can still buy tickets. The veteran ...

Rare Smithsonian artifacts are on display at museums across the country. Mark Strauss This SR-10F Reliant, one of only 18 of this model, participated in airmail pick-up experiments for All American ...

Abstract: Controllable head avatar reconstruction via the inversion of few-shot images using 3D generative models has demonstrated significant potential for efficient avatar creation. However, under ...