Loading video...

Video Failed to Load

Go Home

Feature4X Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

_akhaliq's profile picture

AK

513,832 subscribers

13,911 views • 1 year ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

2 Comments

AK's profile picture
AK1 year ago

discuss:

NICE's profile picture
NICE1 year ago

Stay competitive by balancing cutting-edge AI with automation tools. Forrester shows how.

Related Videos

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.
5:19

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.

MrNeRF

34,782 views • 1 year ago

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS
0:49

A video is compressed 4D data. 🌍 Today, we’re sharing a preview of our latest research: 4D reconstruction from a single monocular video. 🎬 From one casually captured video, our system reconstructs a dynamic, freely viewable 4D Gaussian scene—recovering geometry, appearance, camera motion, and object motion across space and time. No multi-camera rig. Just video → 4DGS. The world has already been captured in video. The next step is to unlock the 4D structure inside it. Watch the result below. 👇 #4DGS #GaussianSplatting #CVPR #CVPR2026 #AIGC #AI #3DGS

InSpatio｜影溯

59,139 views • 8 days ago

omg.. this cant be real China’s 4DV AI just dropped 4D Gaussian Splatting, you can turn 2D video into 4D with sound.. imagine.. we will be able to change camera angle, zoom in/out while watching movies 5 examples:
0:25

omg.. this cant be real China’s 4DV AI just dropped 4D Gaussian Splatting, you can turn 2D video into 4D with sound.. imagine.. we will be able to change camera angle, zoom in/out while watching movies 5 examples:

el.cine

3,612,083 views • 1 year ago

3D gaussian splatting + time (video) = 4D gaussian splatting is now possible This means in the near future you'll be able to fly around on your phone in any video you recorded A lot like the "braindance" in Cyberpunk 2077
0:29

3D gaussian splatting + time (video) = 4D gaussian splatting is now possible This means in the near future you'll be able to fly around on your phone in any video you recorded A lot like the "braindance" in Cyberpunk 2077

@levelsio

590,061 views • 1 year ago

Bridging to Sui? Experience seamless integration with our one-click bridging. Any token, any chain 🌊
0:21

Bridging to Sui? Experience seamless integration with our one-click bridging. Any token, any chain 🌊

OKX Wallet

20,888 views • 1 year ago

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.
0:29

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.

MrNeRF

10,961 views • 1 year ago

One hook connects any Agent to your frontend Then layer on chat UI, threads, generative UI, voice transcription, tool calls, state sync, HITL, and any AI feature. We make it easy for devs to build fullstack agentic apps. Everything here is built with CopilotKit 👇
0:37

One hook connects any Agent to your frontend Then layer on chat UI, threads, generative UI, voice transcription, tool calls, state sync, HITL, and any AI feature. We make it easy for devs to build fullstack agentic apps. Everything here is built with CopilotKit 👇

CopilotKit🪁

20,520 views • 2 months ago

this video cost $3.50 to produce with Algrow's upcoming ai video generation feature
0:25

this video cost $3.50 to produce with Algrow's upcoming ai video generation feature

sam

23,550 views • 5 months ago

Framestore released a BTS breakdown for ‘SUPERMAN,’ revealing the first-ever use of 4D Gaussian Splatting in a feature film. The technique volumetrically captured Bradley Cooper and Angela Sarafyan, creating photoreal “living photography” holograms with full post flexibility.
2:33

Framestore released a BTS breakdown for ‘SUPERMAN,’ revealing the first-ever use of 4D Gaussian Splatting in a feature film. The technique volumetrically captured Bradley Cooper and Angela Sarafyan, creating photoreal “living photography” holograms with full post flexibility.

DC Film News

38,712 views • 5 months ago

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at any time to any view at any other time? Introducing 4D-LRM: a Large Space-Time Reconstruction Model that ... 🔹 Predicts 4D Gaussian primitives directly from multi-view tokens (no motion vectors, no HexPlane); 🔹 Uses a clean, minimal Transformer backbone; 🔹 Generalizes with fast, high-quality feedforward rendering at any view and infinite frame rate. Check out more interactive demos and scaling behaviors on our homepage/paper. 👉Website: 👉Paper:
2:30

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at any time to any view at any other time? Introducing 4D-LRM: a Large Space-Time Reconstruction Model that ... 🔹 Predicts 4D Gaussian primitives directly from multi-view tokens (no motion vectors, no HexPlane); 🔹 Uses a clean, minimal Transformer backbone; 🔹 Generalizes with fast, high-quality feedforward rendering at any view and infinite frame rate. Check out more interactive demos and scaling behaviors on our homepage/paper. 👉Website: 👉Paper:

Martin Ziqiao Ma

21,811 views • 1 year ago

🤖 wake up, new 4d tool! Take any normal 2D video → instantly turn it into fully explorable 3D space. You can now orbit, tilt, and view the scene from angles that literally never existed in the original footage. This is 4D Gaussian Splatting (from 4dv) and it’s next-level.
0:22

🤖 wake up, new 4d tool! Take any normal 2D video → instantly turn it into fully explorable 3D space. You can now orbit, tilt, and view the scene from angles that literally never existed in the original footage. This is 4D Gaussian Splatting (from 4dv) and it’s next-level.

filipe

66,336 views • 2 months ago

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!
2:16

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!

Eric Jing

8,093,558 views • 1 year ago

“Any model, any agent, any accelerator, and any cloud.” Red Hat’s Brian Stevens explains why open AI infrastructure matters as enterprises scale agentic AI workloads, and how Red Hat and AMD are collaborating to help simplify deployment with AMD EPYC processors and AMD Instinct GPUs. Watch the full video on YouTube:
1:02

“Any model, any agent, any accelerator, and any cloud.” Red Hat’s Brian Stevens explains why open AI infrastructure matters as enterprises scale agentic AI workloads, and how Red Hat and AMD are collaborating to help simplify deployment with AMD EPYC processors and AMD Instinct GPUs. Watch the full video on YouTube:

AMD

17,208 views • 2 months ago

Can we apply diffusion directly on MLP weights? Yes!!! We show generalization to new 3D shapes and 4D mesh animations: "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion" #ICCV2023! Project: Video:
0:20

Can we apply diffusion directly on MLP weights? Yes!!! We show generalization to new 3D shapes and 4D mesh animations: "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion" #ICCV2023! Project: Video:

Matthias Niessner

86,046 views • 3 years ago

From 2 second (faster on higher end GPUs) Gaussian splat generations, using Apple's "Sharp Monocular View Synthesis in Less Than a Second" code, running locally on my system. Imported into Octane Render 2026 which has fully path traced rendering of Gaussian splats. Stuff like this is why I've been so excited to see where Gaussian splatting research would go. Combined with a real-time Generative AI "renderer" this stuff could start to get quite insane. Combined with Dreams it would be even better ofc :D Code to the Apple code in the comments below.
0:33

From 2 second (faster on higher end GPUs) Gaussian splat generations, using Apple's "Sharp Monocular View Synthesis in Less Than a Second" code, running locally on my system. Imported into Octane Render 2026 which has fully path traced rendering of Gaussian splats. Stuff like this is why I've been so excited to see where Gaussian splatting research would go. Combined with a real-time Generative AI "renderer" this stuff could start to get quite insane. Combined with Dreams it would be even better ofc :D Code to the Apple code in the comments below.

Martin Nebelong

36,774 views • 7 months ago

This is very cool --> Framestore showcases the 4D Gaussian Splatting used for ‘Superman’. A new video breaks down their collaboration with Infinite-Realities. Watch in full at befores & afters: Stephane Ceretti
0:47

This is very cool --> Framestore showcases the 4D Gaussian Splatting used for ‘Superman’. A new video breaks down their collaboration with Infinite-Realities. Watch in full at befores & afters: Stephane Ceretti

befores & afters magazine

13,895 views • 5 months ago

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs
0:29

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs

Stijn Spanhove

20,127 views • 7 months ago

Ever wanted to create 3D environments without having to do any modeling or use any models? 🤔 Corridor shows us how it's done with gaussian splats using their Puget Systems NVIDIA RTX AI PC. Watch now 👉
2:16

Ever wanted to create 3D environments without having to do any modeling or use any models? 🤔 Corridor shows us how it's done with gaussian splats using their Puget Systems NVIDIA RTX AI PC. Watch now 👉

NVIDIA Studio

30,341 views • 1 year ago

🚀 Instantly create your own AI companions with #Rodin Gen-1.5! Elon Musk, any plans to bring this feature to Grok? 🤔 #Grok4
1:09

🚀 Instantly create your own AI companions with #Rodin Gen-1.5! Elon Musk, any plans to bring this feature to Grok? 🤔 #Grok4

Deemos

267,245 views • 1 year ago