Loading video...

Video Failed to Load

Go Home

๐Ÿ“ข๐Ÿ“ข Video Diffusion Avatars๐Ÿ“ข๐Ÿ“ข Can video diffusion models (VDMs) replace 3D avatars? Video Diffusion Avatars (VDA) creates photo-realistic avatars from a single image, with full control over camera viewpoint, facial expressions and upper-body pose. Unlike prevailing 3D avatar methods, which commonly rely on 3DGS/NeRF, our VDM-rendering produces physically plausible...

MattNiessner's profile picture

Matthias Niessner

50,506 subscribers

17,715 views โ€ข 4 days ago โ€ขvia X (Twitter)

LIVE

Anya Rossiโ€ข Live Now

Private livecam show

3 Comments

Abdullah Hamdi's profile picture
Abdullah Hamdi4 days ago

Awsome !

Matthias Niessner's profile picture
Matthias Niessner4 days ago

Thanks :)

m's profile picture
m3 days ago

Interesting, but too slow because of WAN2...

Related Videos

(1/2) ๐Ÿ“ข๐Ÿ“ข๐ƒ๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง๐€๐ฏ๐š๐ญ๐š๐ซ๐ฌ ๐Ÿ“ข๐Ÿ“ข High-fidelity 3D head avatars with precise control over viewpoint, expression, and pose. -> Our parametric 3D model enables control & consistency + 2D diffusion makes it photoreal.
0:32

(1/2) ๐Ÿ“ข๐Ÿ“ข๐ƒ๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง๐€๐ฏ๐š๐ญ๐š๐ซ๐ฌ ๐Ÿ“ข๐Ÿ“ข High-fidelity 3D head avatars with precise control over viewpoint, expression, and pose. -> Our parametric 3D model enables control & consistency + 2D diffusion makes it photoreal.

Matthias Niessner

66,436 views โ€ข 2 years ago

๐Ÿ“ข๐Ÿ“ข ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง๐’๐ฉ๐ž๐ž๐œ๐ก: Audio-Driven Gaussian Avatars ๐Ÿ“ข๐Ÿ“ข We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of โˆผ3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai
0:33

๐Ÿ“ข๐Ÿ“ข ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง๐’๐ฉ๐ž๐ž๐œ๐ก: Audio-Driven Gaussian Avatars ๐Ÿ“ข๐Ÿ“ข We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of โˆผ3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

Matthias Niessner

22,703 views โ€ข 1 year ago

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.
6:20

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.

AK

327,415 views โ€ข 2 years ago

๐Ÿ“ข๐Ÿ“ข ๐€๐ฏ๐š๐ญ๐Ÿ‘๐ซ ๐Ÿ“ข๐Ÿ“ข Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito
0:38

๐Ÿ“ข๐Ÿ“ข ๐€๐ฏ๐š๐ญ๐Ÿ‘๐ซ ๐Ÿ“ข๐Ÿ“ข Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,863 views โ€ข 1 year ago

๐Ÿ“ขBecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading We propose a hybrid neural shading scheme for creating intrinsically decomposed 3DGS head avatars, that allow real-time relighting and animation. ๐ŸŒ ๐Ÿ“ท
0:24

๐Ÿ“ขBecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading We propose a hybrid neural shading scheme for creating intrinsically decomposed 3DGS head avatars, that allow real-time relighting and animation. ๐ŸŒ ๐Ÿ“ท

Matthias Niessner

23,040 views โ€ข 1 year ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขData release: high-res, multi-view, OLAT face recordings ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain
0:31

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขData release: high-res, multi-view, OLAT face recordings ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain

Matthias Niessner

19,536 views โ€ข 9 months ago

MVDream: Multi-view Diffusion for 3D Generation paper page: propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on large-scale web datasets and a multi-view dataset rendered from 3D assets, the resulting multi-view diffusion model can achieve both the generalizability of 2D diffusion and the consistency of 3D data. Such a model can thus be applied as a multi-view prior for 3D generation via Score Distillation Sampling, where it greatly improves the stability of existing 2D-lifting methods by solving the 3D consistency problem. Finally, we show that the multi-view diffusion model can also be fine-tuned under a few shot setting for personalized 3D generation, i.e. DreamBooth3D application, where the consistency can be maintained after learning the subject identity.
0:44

MVDream: Multi-view Diffusion for 3D Generation paper page: propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on large-scale web datasets and a multi-view dataset rendered from 3D assets, the resulting multi-view diffusion model can achieve both the generalizability of 2D diffusion and the consistency of 3D data. Such a model can thus be applied as a multi-view prior for 3D generation via Score Distillation Sampling, where it greatly improves the stability of existing 2D-lifting methods by solving the 3D consistency problem. Finally, we show that the multi-view diffusion model can also be fine-tuned under a few shot setting for personalized 3D generation, i.e. DreamBooth3D application, where the consistency can be maintained after learning the subject identity.

AK

294,519 views โ€ข 3 years ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐‚๐Ÿ‘๐ƒ: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers TL;DR: for 3D camera control in generative video, it really helps knowing *which* part of your model you should mess with Internship by Sherwin Bahmani at Snap
0:40

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐‚๐Ÿ‘๐ƒ: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers TL;DR: for 3D camera control in generative video, it really helps knowing *which* part of your model you should mess with Internship by Sherwin Bahmani at Snap

Andrea Tagliasacchi

23,088 views โ€ข 1 year ago

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:
1:22

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:

AK

263,035 views โ€ข 3 years ago

Source code released: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
0:21

Source code released: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

MrNeRF

18,357 views โ€ข 2 years ago

Super excited for #ECCV'26 in Malmรถ! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lรผtzow Haoxuan Li Ziya Erkoรง Umut Kocasarฤฑ Vanessa Sklyarova Lukas Hรถllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!
0:27

Super excited for #ECCV'26 in Malmรถ! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lรผtzow Haoxuan Li Ziya Erkoรง Umut Kocasarฤฑ Vanessa Sklyarova Lukas Hรถllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!

Matthias Niessner

15,338 views โ€ข 1 month ago

ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based local expression features and increase the representation capacity by synthesizing 3D Gaussians dynamically by leveraging tiny scaffold MLPs conditioned on localized expressions. We further propose a color-based densification and progressive training scheme for improved quality and faster convergence. Project: Video: Great work by Shivangi, Sebastian Weiss, Irene Baeza, Prashanth Chandran, Gaspard Zoss, Derek Bradley
0:37

ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based local expression features and increase the representation capacity by synthesizing 3D Gaussians dynamically by leveraging tiny scaffold MLPs conditioned on localized expressions. We further propose a color-based densification and progressive training scheme for improved quality and faster convergence. Project: Video: Great work by Shivangi, Sebastian Weiss, Irene Baeza, Prashanth Chandran, Gaspard Zoss, Derek Bradley

Matthias Niessner

17,318 views โ€ข 1 year ago

Mirage just dropped Avatar X, a new model for AI avatars. It creates avatars that actually look, sound and react like you, with lifelike micro-expressions and body language. Avatar X shines on identity preservation for both vertical and horizontal video, capturing subtle expressions and naturally handling moments like laughing. And unlike other avatar models, the quality stays sharp and consistent from the first frame to the last. This is getting way too real. Try it here โ†’
0:27

Mirage just dropped Avatar X, a new model for AI avatars. It creates avatars that actually look, sound and react like you, with lifelike micro-expressions and body language. Avatar X shines on identity preservation for both vertical and horizontal video, capturing subtle expressions and naturally handling moments like laughing. And unlike other avatar models, the quality stays sharp and consistent from the first frame to the last. This is getting way too real. Try it here โ†’

Angry Tom

12,075 views โ€ข 2 months ago

๐Ÿ“ข 3D world models from video diffusion suffer from inconsistent frames -> blurry output. Our fix: instead of naรฏve 3D reconstruction, we non-rigidly align each frame into a globally-consistent 3DGS representation. ->sharp visuals on top of any VDM!
0:29

๐Ÿ“ข 3D world models from video diffusion suffer from inconsistent frames -> blurry output. Our fix: instead of naรฏve 3D reconstruction, we non-rigidly align each frame into a globally-consistent 3DGS representation. ->sharp visuals on top of any VDM!

Matthias Niessner

53,323 views โ€ข 7 months ago

[SIGGRAPH '25] EVA: Expressive Virtual Avatars from Multi-view Videos Contributions: 1. We introduce EVA, a novel method enabling full-body control with real-time, photo-realistic renderings, robustly handling loose clothing dynamics and various facial expressions. 2. We develop an expressive deformable template that generates a deformable human template mesh and employs a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.
1:22

[SIGGRAPH '25] EVA: Expressive Virtual Avatars from Multi-view Videos Contributions: 1. We introduce EVA, a novel method enabling full-body control with real-time, photo-realistic renderings, robustly handling loose clothing dynamics and various facial expressions. 2. We develop an expressive deformable template that generates a deformable human template mesh and employs a multi-stage tracking algorithm to faithfully capture facial expressions, body motions, and non-rigid deformations from multi-view videos. 3. We propose a disentangled 3D Gaussian appearance module that models the body and face independently, ensuring separated control and high-quality renderings.

MrNeRF

18,502 views โ€ข 1 year ago

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360ยฐ, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360ยฐ head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data ๐Ÿ  ๐ŸŒ ๐ŸŽฅ Great work by Tobias Kirschstein and Simon Giebenhain!
0:30

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360ยฐ, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360ยฐ head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data ๐Ÿ  ๐ŸŒ ๐ŸŽฅ Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 views โ€ข 10 months ago

Want to have explicit control over skeletal pose, facial expressions, and hand gestures for your photorealistic virtual avatar that can be learned from multi-view video? Check out our #Siggraph2025 work, EVA, which presents an expressive, full-body, and photorealistic avatar.
1:22

Want to have explicit control over skeletal pose, facial expressions, and hand gestures for your photorealistic virtual avatar that can be learned from multi-view video? Check out our #Siggraph2025 work, EVA, which presents an expressive, full-body, and photorealistic avatar.

Marc Habermann

12,534 views โ€ข 1 year ago

DimensionX Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
1:49

DimensionX Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

AK

58,273 views โ€ข 1 year ago

๐Ÿ“ข Check out ๐—ฅ๐—ฒ๐—น๐—ถ๐—ด๐—ต๐˜๐—ฎ๐—ฏ๐—น๐—ฒ ๐—š๐—ฎ๐˜‚๐˜€๐˜€๐—ถ๐—ฎ๐—ป ๐—–๐—ผ๐—ฑ๐—ฒ๐—ฐ ๐—”๐˜ƒ๐—ฎ๐˜๐—ฎ๐—ฟ๐˜€! Our latest codec avatars using 3D Gaussians generalize to novel lighting (OLAT, envmap) with *all-frequency* reflection (see video for hair and eye reflection) in real-time!
0:43

๐Ÿ“ข Check out ๐—ฅ๐—ฒ๐—น๐—ถ๐—ด๐—ต๐˜๐—ฎ๐—ฏ๐—น๐—ฒ ๐—š๐—ฎ๐˜‚๐˜€๐˜€๐—ถ๐—ฎ๐—ป ๐—–๐—ผ๐—ฑ๐—ฒ๐—ฐ ๐—”๐˜ƒ๐—ฎ๐˜๐—ฎ๐—ฟ๐˜€! Our latest codec avatars using 3D Gaussians generalize to novel lighting (OLAT, envmap) with *all-frequency* reflection (see video for hair and eye reflection) in real-time!

Shunsuke Saito

46,029 views โ€ข 2 years ago