Pixel codec avatars
… visible pixels from the corresponding views; in the second row we show the … avatars and
the percentage of pixels they cover over the entire image. the decoder decodes the avatar’s …
the percentage of pixels they cover over the entire image. the decoder decodes the avatar’s …
Relightable gaussian codec avatars
… a method to build high-fidelity relightable head avatars that can be animated to generate …
avatars on a tethered consumer VR headset showcasing the efficiency and fidelity of our avatars…
avatars on a tethered consumer VR headset showcasing the efficiency and fidelity of our avatars…
POCA: Post-training Quantization with Temporal Alignment for Codec Avatars
… and rendering the avatar in real-time. In practice, the VAE-based Codec Avatar model
has been employed for generative Pixel Codec Avatar [15] or 3D Gaussian-based Avatar [22]. …
has been employed for generative Pixel Codec Avatar [15] or 3D Gaussian-based Avatar [22]. …
URAvatar: Universal Relightable Gaussian Codec Avatars
… For each identity in our training dataset, we therefore fit a personalized pixel codec avatar
… Leveraging the dense position map-based geometry representation and perpixel color …
… Leveraging the dense position map-based geometry representation and perpixel color …
Expressive telepresence via modular codec avatars
… This paper proposes Modular Codec Avatar (MCA) that improves robustness and … of the
pixels corresponding to the same closest mesh vertex instead of averaging over all pixels on the …
pixels corresponding to the same closest mesh vertex instead of averaging over all pixels on the …
Universal Facial Encoding of Codec Avatars from VR Headsets
… avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication,
avatar … In this paper, we present a method that can animate a photorealistic avatar in realtime …
avatar … In this paper, we present a method that can animate a photorealistic avatar in realtime …
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence
… We benchmark both quantitative reconstruction quality, in terms of the MSE between the
rasterized pixels of the rendered avatars and the ground truth, and qualitative rendering quality, …
rasterized pixels of the rendered avatars and the ground truth, and qualitative rendering quality, …
System-level design and integration of a prototype AR/VR hardware featuring a custom low-power DNN accelerator chip in 7nm technology for codec avatars
… avatars, referred to as “Codec Avatars”. Delivering a high visual performance for Codec
Avatar … performance for running eye gaze extraction of the Codec Avatar model. The test-chip, …
Avatar … performance for running eye gaze extraction of the Codec Avatar model. The test-chip, …
Multiface: A dataset for neural face rendering
… , we provide code to train a Codec Avatar from scratch as well as pretrained Codec … Finally,
Pixel Codec Avatars [11] provide a lightweight model that can render photorealistic avatars …
Pixel Codec Avatars [11] provide a lightweight model that can render photorealistic avatars …
GenCA: A Text-conditioned Generative Model for Realistic and Drivable Codec Avatars
… for avatar expression driving. Our model can generate and control high-fidelity avatars, even
… for downstream applications, including avatar editing and single-shot avatar reconstruction. …
… for downstream applications, including avatar editing and single-shot avatar reconstruction. …