State of the art on neural rendering
Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer
graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic …
graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic …
Eye tracking in virtual reality: a broad review of applications and challenges
Eye tracking is becoming increasingly available in head-mounted virtual reality displays with
various headsets with integrated eye trackers already commercially available. The …
various headsets with integrated eye trackers already commercially available. The …
Rodin: A generative model for sculpting 3d digital avatars using diffusion
This paper presents a 3D diffusion model that automatically generates 3D digital avatars
represented as neural radiance fields (NeRFs). A significant challenge for 3D diffusion is …
represented as neural radiance fields (NeRFs). A significant challenge for 3D diffusion is …
Gaussian head avatar: Ultra high-fidelity head avatar via dynamic gaussians
Creating high-fidelity 3D head avatars has always been a research hotspot but there
remains a great challenge under lightweight sparse view setups. In this paper we propose …
remains a great challenge under lightweight sparse view setups. In this paper we propose …
Fastnerf: High-fidelity neural rendering at 200fps
Abstract Recent work on Neural Radiance Fields (NeRF) showed how neural networks can
be used to encode complex 3D environments that can be rendered photorealistically from …
be used to encode complex 3D environments that can be rendered photorealistically from …
Neural head avatars from monocular rgb videos
Abstract We present Neural Head Avatars, a novel neural representation that explicitly
models the surface geometry and appearance of an animatable human avatar that can be …
models the surface geometry and appearance of an animatable human avatar that can be …
Expressive talking head generation with granular audio-visual control
Generating expressive talking heads is essential for creating virtual humans. However,
existing one-or few-shot methods focus on lip-sync and head motion, ignoring the emotional …
existing one-or few-shot methods focus on lip-sync and head motion, ignoring the emotional …
Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization
Recent advances in image-based 3D human shape estimation have been driven by the
significant improvement in representation power afforded by deep neural networks …
significant improvement in representation power afforded by deep neural networks …
Arch++: Animation-ready clothed human reconstruction revisited
We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary
clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both …
clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both …
H-nerf: Neural radiance fields for rendering and temporal reconstruction of humans in motion
H Xu, T Alldieck… - Advances in Neural …, 2021 - proceedings.neurips.cc
We present neural radiance fields for rendering and temporal (4D) reconstruction of humans
in motion (H-NeRF), as captured by a sparse set of cameras or even from a monocular …
in motion (H-NeRF), as captured by a sparse set of cameras or even from a monocular …