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.

Happy to share "Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures"! DUT generates photoreal novel view 4K human renderings in real-time.🥳 Project page:

Marc Habermann

1,738 subscribers

16,872 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

4 Comments

Marc Habermann1 year ago

Team: @GuoxingSun @wootwootwo @FuaPv @rishabh_dabral Christian

Marc Habermann1 year ago

The key idea is to use sparse-view image information to robustly estimate coarse geometry deformation in texel space and to perform a second texture unprojection with refined geometry for better texture alignment and more faithful renderings.

Akool Inc1 year ago

AI has made it easy for anyone to create realistic avatar videos without expensive gear. AKOOL and Synthesia are top choices for AI-generated "talking photo" videos. Which one is best for your team?

Tom Boyle1 year ago

Incredible work! How robust is this method when applied to more dynamic or cluttered environments?

Related Videos

3D view of the human body from head to toe, compiled using 5,100 anatomical sections from the Visible Human Project 🩻🧠 📽️: Kentskooking

3D view of the human body from head to toe, compiled using 5,100 anatomical sections from the Visible Human Project 🩻🧠 📽️: Kentskooking

Keith Siau

52,661 views • 1 year 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.

[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

18,407 views • 1 year ago

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:

Haian Jin

114,872 views • 1 year ago

Our new work PSHuman reconstructs a detailed 3D human mesh from a single-view image in ~1min. Codes have already been released! Welcome to try it! Project page: Codes: Paper:

Our new work PSHuman reconstructs a detailed 3D human mesh from a single-view image in ~1min. Codes have already been released! Welcome to try it! Project page: Codes: Paper:

Yuan Liu

53,252 views • 1 year ago

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

Yuan Liu

79,610 views • 1 year ago

Project Genie is a Google Labs experiment that lets you simulate dynamic worlds you can navigate in real time with Genie, our general-purpose world model. Today, we’re connecting Project Genie to nearly 20 years of Street View data from Google Maps — so you can now build interactive spaces based on real-world locations. Street View imagery in Project Genie is available now for places in the U.S., and will expand to more locales over time. #GoogleIO

Project Genie is a Google Labs experiment that lets you simulate dynamic worlds you can navigate in real time with Genie, our general-purpose world model. Today, we’re connecting Project Genie to nearly 20 years of Street View data from Google Maps — so you can now build interactive spaces based on real-world locations. Street View imagery in Project Genie is available now for places in the U.S., and will expand to more locales over time. #GoogleIO

Google

177,069 views • 3 months ago

The free AVATAR project is expected to launch for testing this week, offering cinematic-quality real-time rendering. You can create personalized characters and even connect with free AI motion capture to produce high-quality real-time animation using a 1080P webcam.

CYANPUPPETS

41,033 views • 1 year ago

🔥 Introducing MVLift: Generate realistic 3D motion without any 3D training data - just using 2D poses from monocular videos! Applicable to human motion, human-object interaction & animal motion. Joint work w/ Jiajun Wu & Karen 💡 How? We reformulate 3D motion estimation as generating consistent multi-view 2D pose sequences. Our framework uses 2D motion diffusion to progressively establish multi-view consistency, requiring only single-view 2D pose sequences for training. Project: Video with demonstration: Paper:

🔥 Introducing MVLift: Generate realistic 3D motion without any 3D training data - just using 2D poses from monocular videos! Applicable to human motion, human-object interaction & animal motion. Joint work w/ Jiajun Wu & Karen 💡 How? We reformulate 3D motion estimation as generating consistent multi-view 2D pose sequences. Our framework uses 2D motion diffusion to progressively establish multi-view consistency, requiring only single-view 2D pose sequences for training. Project: Video with demonstration: Paper:

Jiaman Li

15,886 views • 1 year ago

MIT’s TRANSFORM project turns ordinary surfaces into shape shifting displays that respond to human touch in real time.

MIT’s TRANSFORM project turns ordinary surfaces into shape shifting displays that respond to human touch in real time.

Science girl

1,090,746 views • 6 months ago

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian Contributions: • We propose a novel scene representation for accurately modeling complex near-field and high-frequency reflections in real-world environments. • We developed a real-time ray-tracing renderer for 2DGS, enabling joint optimization of our representation for accurate scene reconstruction while achieving real-time rendering speeds. • Extensive experiments show that EnvGS significantly outperforms previous methods. To the best of our knowledge, EnvGS is the first method to achieve real-time photorealistic specular reflections synthesis in real-world scenes.

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian Contributions: • We propose a novel scene representation for accurately modeling complex near-field and high-frequency reflections in real-world environments. • We developed a real-time ray-tracing renderer for 2DGS, enabling joint optimization of our representation for accurate scene reconstruction while achieving real-time rendering speeds. • Extensive experiments show that EnvGS significantly outperforms previous methods. To the best of our knowledge, EnvGS is the first method to achieve real-time photorealistic specular reflections synthesis in real-world scenes.

MrNeRF

44,878 views • 1 year ago

Introducing OpenEditor, a Figma like canvas to preview code projects in real time. - It is a performant desktop app that enables you to see your app from a bird's eye view. - Instantly view changes across different breakpoints, app states and environments.

Introducing OpenEditor, a Figma like canvas to preview code projects in real time. - It is a performant desktop app that enables you to see your app from a bird's eye view. - Instantly view changes across different breakpoints, app states and environments.

Dami Dina

59,347 views • 6 months ago

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

Fast View Synthesis of Casual Videos paper page: Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and render. This paper revisits explicit video representations to synthesize high-quality novel views from a monocular video efficiently. We treat static and dynamic video content separately. Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video. Our plane-based scene representation is augmented with spherical harmonics and displacement maps to capture view-dependent effects and model non-planar complex surface geometry. We opt to represent the dynamic content as per-frame point clouds for efficiency. While such representations are inconsistency-prone, minor temporal inconsistencies are perceptually masked due to motion. We develop a method to quickly estimate such a hybrid video representation and render novel views in real time. Our experiments show that our method can render high-quality novel views from an in-the-wild video with comparable quality to state-of-the-art methods while being 100x faster in training and enabling real-time rendering.

AK

20,668 views • 2 years ago

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:

AIT Lab

14,619 views • 3 years ago

Live view counters just got better! - sort by most-viewed in real-time on new screener - view counters now added to every coin on Trenches columns Switch to Terminal for NEW features that give YOU more edge.

Live view counters just got better! - sort by most-viewed in real-time on new screener - view counters now added to every coin on Trenches columns Switch to Terminal for NEW features that give YOU more edge.

Terminal

44,885 views • 8 months ago

Introducing Phoenix-4, the most advanced real-time human rendering model ever built. Its the first real-time model to render every pixel at runtime, generate and control emotional states, listen actively, and actually behave the way humans do in conversation.

Introducing Phoenix-4, the most advanced real-time human rendering model ever built. Its the first real-time model to render every pixel at runtime, generate and control emotional states, listen actively, and actually behave the way humans do in conversation.

Tavus

2,087,720 views • 6 months ago

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery TL;DR: Skyfall-GS converts satellite images to explorable 3D urban scenes using diffusion models, with real-time rendering performance. Contributions: • We introduce Skyfall-GS, the first method to synthesize immersive, real-time, free-flight navigable 3D urban scenes solely from multi-view satellite imagery using generative refinement. • An open-domain refinement approach leverages pre-trained text-to-image diffusion models without domain-specific training. • A curriculum-learning-based iterative refinement strategy progressively enhances reconstruction quality from higher to lower viewpoints, significantly improving visual fidelity in occluded areas.

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery TL;DR: Skyfall-GS converts satellite images to explorable 3D urban scenes using diffusion models, with real-time rendering performance. Contributions: • We introduce Skyfall-GS, the first method to synthesize immersive, real-time, free-flight navigable 3D urban scenes solely from multi-view satellite imagery using generative refinement. • An open-domain refinement approach leverages pre-trained text-to-image diffusion models without domain-specific training. • A curriculum-learning-based iterative refinement strategy progressively enhances reconstruction quality from higher to lower viewpoints, significantly improving visual fidelity in occluded areas.

MrNeRF

66,311 views • 10 months ago

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,804 views • 5 months ago