@tkirschstein.bsky.social
Reposted
(3/3)
We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours.
shivangi-aneja.github.io/projects/gau...
youtu.be/2VqYoFlYcwQ
Great work by Shivangi Aneja, Artem Sevastopolsky, @tkirschstein.bsky.social , Justus Thies, @adai.bsky.social
We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours.
shivangi-aneja.github.io/projects/gau...
youtu.be/2VqYoFlYcwQ
Great work by Shivangi Aneja, Artem Sevastopolsky, @tkirschstein.bsky.social , Justus Thies, @adai.bsky.social
GaussianSpeech: Audio-Driven Gaussian Avatars
shivangi-aneja.github.io
December 2, 2024 at 11:08 AM
(3/3)
We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours.
shivangi-aneja.github.io/projects/gau...
youtu.be/2VqYoFlYcwQ
Great work by Shivangi Aneja, Artem Sevastopolsky, @tkirschstein.bsky.social , Justus Thies, @adai.bsky.social
We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours.
shivangi-aneja.github.io/projects/gau...
youtu.be/2VqYoFlYcwQ
Great work by Shivangi Aneja, Artem Sevastopolsky, @tkirschstein.bsky.social , Justus Thies, @adai.bsky.social
(4/4)
As 3D Gaussians are sensitive to adversarial training, we introduce tailored regularization strategies and a UV total variation loss to facilitate high geometric fidelity of the generated heads.
Collaboration with Simon Giebenhain, Jiapeng Tang, Markos Georgopoulos and @niessner.bsky.social
As 3D Gaussians are sensitive to adversarial training, we introduce tailored regularization strategies and a UV total variation loss to facilitate high geometric fidelity of the generated heads.
Collaboration with Simon Giebenhain, Jiapeng Tang, Markos Georgopoulos and @niessner.bsky.social
November 28, 2024 at 2:59 PM
(4/4)
As 3D Gaussians are sensitive to adversarial training, we introduce tailored regularization strategies and a UV total variation loss to facilitate high geometric fidelity of the generated heads.
Collaboration with Simon Giebenhain, Jiapeng Tang, Markos Georgopoulos and @niessner.bsky.social
As 3D Gaussians are sensitive to adversarial training, we introduce tailored regularization strategies and a UV total variation loss to facilitate high geometric fidelity of the generated heads.
Collaboration with Simon Giebenhain, Jiapeng Tang, Markos Georgopoulos and @niessner.bsky.social
(3/4)
We learn to generate photo-realistic 3D heads only from training on 2D images. In contrast to existing works such as EG3D, we leverage the efficient rasterization of 3D Gaussians, thus mitigating the need for any 2D super-resolution networks.
-> enforcing view consistency.
We learn to generate photo-realistic 3D heads only from training on 2D images. In contrast to existing works such as EG3D, we leverage the efficient rasterization of 3D Gaussians, thus mitigating the need for any 2D super-resolution networks.
-> enforcing view consistency.
November 28, 2024 at 2:59 PM
(3/4)
We learn to generate photo-realistic 3D heads only from training on 2D images. In contrast to existing works such as EG3D, we leverage the efficient rasterization of 3D Gaussians, thus mitigating the need for any 2D super-resolution networks.
-> enforcing view consistency.
We learn to generate photo-realistic 3D heads only from training on 2D images. In contrast to existing works such as EG3D, we leverage the efficient rasterization of 3D Gaussians, thus mitigating the need for any 2D super-resolution networks.
-> enforcing view consistency.
(2/4)
We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.
Also see our project page: tobias-kirschstein.github.io/gghead/
and video: youtu.be/M5vq3DoZ7RI
We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.
Also see our project page: tobias-kirschstein.github.io/gghead/
and video: youtu.be/M5vq3DoZ7RI
GGHead: Fast and Generalizable 3D Gaussian Heads
GGHead: Fast and Generalizable 3D Gaussian Heads
tobias-kirschstein.github.io
November 28, 2024 at 2:59 PM
(2/4)
We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.
Also see our project page: tobias-kirschstein.github.io/gghead/
and video: youtu.be/M5vq3DoZ7RI
We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time.
Also see our project page: tobias-kirschstein.github.io/gghead/
and video: youtu.be/M5vq3DoZ7RI