Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

📢DNF: Generating 4D animations with dictionary-based neural fields! Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.

Angela Dai

9,539 subscribers

14,639 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Text-To-4D Dynamic Scene Generation Presents MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. proj: abs:

Text-To-4D Dynamic Scene Generation Presents MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. proj: abs:

Aran Komatsuzaki

54,664 views • 3 years ago

General relativity 🤝 neural fields This simulation of a black hole is coming from our neural networks 🚀 We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.

General relativity 🤝 neural fields This simulation of a black hole is coming from our neural networks 🚀 We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.

Johannes Brandstetter

39,368 views • 11 months ago

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

MrNeRF

17,035 views • 4 months ago

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

Andrea Tagliasacchi @CVPR

16,962 views • 1 year ago

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field Contributions: 1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios. 2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view. 3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity. 4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field Contributions: 1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios. 2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view. 3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity. 4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.

MrNeRF

10,607 views • 1 year ago

"HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion" Constructs temporal NeRF of humans from multi-view video Impressive quality. Easy to see applications in gaming - better avatar creation etc.

Jay Hack

54,055 views • 3 years ago

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions paper page: present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions paper page: present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.

AK

194,462 views • 2 years ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,039 views • 1 year ago

Pls RT: We’re hiring a research tech to work with us on the neural basis of cuttlefish camouflage! We’re generating transgenics, doing neural imaging and behavior in these cute cephalopods. Soon-to-be and recent grads encouraged to apply to our team. Info:

Pls RT: We’re hiring a research tech to work with us on the neural basis of cuttlefish camouflage! We’re generating transgenics, doing neural imaging and behavior in these cute cephalopods. Soon-to-be and recent grads encouraged to apply to our team. Info:

Tessa Montague

422,540 views • 3 years ago

A new class of reasoning-based video models for professional video production, delivering seamless 8K videos with studio-grade HDR and precise hybrid AI performance. Maximum consistency, high speed, and cinematic quality — all within an intuitive interface for beginners.

A new class of reasoning-based video models for professional video production, delivering seamless 8K videos with studio-grade HDR and precise hybrid AI performance. Maximum consistency, high speed, and cinematic quality — all within an intuitive interface for beginners.

Alli Studio

588,454 views • 6 months ago

exploring new animations for generating questions in Inflight

exploring new animations for generating questions in Inflight

Ridd 🤿

19,656 views • 4 months ago

Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: Website:

Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: Website:

Devi Parikh

305,729 views • 3 years ago

✨ Any static 3D assets ➡️ 4D dynamic worlds. Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs. It generalizes surprisingly well across a wide range of objects 🤯 and can even be used to learn robotics manipulation policy 🤖! Project page: Dive deeper in a 🧵: 1/n

✨ Any static 3D assets ➡️ 4D dynamic worlds. Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs. It generalizes surprisingly well across a wide range of objects 🤯 and can even be used to learn robotics manipulation policy 🤖! Project page: Dive deeper in a 🧵: 1/n

Chen Geng

43,132 views • 5 months ago

NeuralGS Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

NeuralGS Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

AK

68,496 views • 1 year ago

Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place. More details ⬇️

Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place. More details ⬇️

AI at Meta

677,765 views • 2 years ago

Introducing DI-PCG: A diffusion-based Image2PCG framework that automates Procedural Content Generation, and our first step towards neural symbolic 3D generation. The demo showcases six object categories and can be extended to support customized PCGs. Links in comments. CC: Wang Zhao

Introducing DI-PCG: A diffusion-based Image2PCG framework that automates Procedural Content Generation, and our first step towards neural symbolic 3D generation. The demo showcases six object categories and can be extended to support customized PCGs. Links in comments. CC: Wang Zhao

Ying Shan

12,420 views • 1 year ago

Check out these fascinating embroidery VFX created using Houdini, Cinema 4D, and Redshift by Alreadybeenchewed.tv. More high-quality VFX:

Check out these fascinating embroidery VFX created using Houdini, Cinema 4D, and Redshift by Alreadybeenchewed.tv. More high-quality VFX:

80 LEVEL

14,653 views • 1 year ago

#BestPaperAwardHonorableMention #SIGGRAPH2025 One neural PDE model, hundreds of cuts and discontinuities — simulated in real time. 🚀 Introducing WindLifter: lifting the winding number fields lets us capture discontinuities in neural fields. Come see ChangYue’s talk today 👉

#BestPaperAwardHonorableMention #SIGGRAPH2025 One neural PDE model, hundreds of cuts and discontinuities — simulated in real time. 🚀 Introducing WindLifter: lifting the winding number fields lets us capture discontinuities in neural fields. Come see ChangYue’s talk today 👉

Peter Yichen Chen

11,483 views • 10 months ago

Trending: Step1X-3D for generating high-fidelity 3D assets with versatile textures! Apache-2.0 with exceptional results in terms of geometry and texture mapping🔥🔥

Trending: Step1X-3D for generating high-fidelity 3D assets with versatile textures! Apache-2.0 with exceptional results in terms of geometry and texture mapping🔥🔥

Gradio

36,405 views • 1 year ago