Загрузка видео...

Не удалось загрузить видео

На главную

"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.

mathemagic1an's profile picture

Jay Hack

70,876 subscribers

54,055 просмотров • 3 лет назад •via X (Twitter)

Здоровье и велнесИгрыНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

📢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.
0:19

📢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

14,637 просмотров • 1 год назад

This is preserved anatomy with Ray3. From faces and hands to bodies in motion, every form stays true. Humans and creatures remain clear and coherent in every action. Retain character structure with high fidelity, holding details together even through complex cinematic scenes.
0:17

This is preserved anatomy with Ray3. From faces and hands to bodies in motion, every form stays true. Humans and creatures remain clear and coherent in every action. Retain character structure with high fidelity, holding details together even through complex cinematic scenes.

Luma AI

60,389 просмотров • 8 месяцев назад

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.
0:19

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,340 просмотров • 1 год назад

Can’t wait for humans to become multi planetary
0:12

Can’t wait for humans to become multi planetary

Tesla Owners Silicon Valley

36,475 просмотров • 5 месяцев назад

Are you at #SIGGRAPH2024 and want to learn how to reconstruct meshes from multi-view images that contain details like individual strands of grass? Then come today to the "Radiance Field Processing" session at 2 p.m. in Mile High 1.
0:11

Are you at #SIGGRAPH2024 and want to learn how to reconstruct meshes from multi-view images that contain details like individual strands of grass? Then come today to the "Radiance Field Processing" session at 2 p.m. in Mile High 1.

Christian Reiser

18,361 просмотров • 1 год назад

Moravec's Paradox is real. What's hard for humans is easy for robots. What's easy for humans is hard for robots. Crazy flip kick but still no humanoids doing useful work in production.
0:10

Moravec's Paradox is real. What's hard for humans is easy for robots. What's easy for humans is hard for robots. Crazy flip kick but still no humanoids doing useful work in production.

Simon Kalouche

84,674 просмотров • 5 месяцев назад

Humans drink milk to see better at night 🐾
0:16

Humans drink milk to see better at night 🐾

ASI Hub

45,118 просмотров • 7 месяцев назад

Cinematic Motion Prompts for Fashion The following prompt examples leverage the composition of our starting image to create high-fidelity video motion. Let's go 👇
0:12

Cinematic Motion Prompts for Fashion The following prompt examples leverage the composition of our starting image to create high-fidelity video motion. Let's go 👇

Marco

26,724 просмотров • 6 месяцев назад

Vidu Q3 is now available on Akool Experience next-level AI video creation with Vidu Q3 — a powerful multi-modal model that seamlessly blends high-fidelity visuals with perfectly synchronized audio. Powered by Vidu AI, Q3 shines in: Deep narrative understanding Mastery of complex cinematic language Lifelike, human-feeling motion and emotion If storytelling and cinematic quality matter to you, Vidu Q3 is built for it. Try it now on Akool.
0:11

Vidu Q3 is now available on Akool Experience next-level AI video creation with Vidu Q3 — a powerful multi-modal model that seamlessly blends high-fidelity visuals with perfectly synchronized audio. Powered by Vidu AI, Q3 shines in: Deep narrative understanding Mastery of complex cinematic language Lifelike, human-feeling motion and emotion If storytelling and cinematic quality matter to you, Vidu Q3 is built for it. Try it now on Akool.

Akool Inc

1,528,560 просмотров • 4 месяцев назад

This is a NeRF (Neural Radiance Field) and it's one of the coolest pieces of AI tech out there. To generate this scene, I shot a video on my iPhone, then uploaded to Luma Luma turned it into a NeRF, and then I directed the camera in their editor to create this shot. Don't sleep on NeRFs.
0:14

This is a NeRF (Neural Radiance Field) and it's one of the coolest pieces of AI tech out there. To generate this scene, I shot a video on my iPhone, then uploaded to Luma Luma turned it into a NeRF, and then I directed the camera in their editor to create this shot. Don't sleep on NeRFs.

Nick St. Pierre

1,026,490 просмотров • 3 лет назад

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians paper page: Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.
0:12

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians paper page: Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.

AK

65,834 просмотров • 2 лет назад

LongCat-Video-Avatar 1.5 is a major upgrade for AI avatar generation. > Better lip-sync + mouth-shape accuracy > Stable identities across long videos & multi-person scenes > Smooth full-body motion, singing, animation, & hand interactions > Outperforms HeyGen, Kling Avatar 2.0, & OmniHuman-1.5 in consistency tests Free & open source
0:13

LongCat-Video-Avatar 1.5 is a major upgrade for AI avatar generation. > Better lip-sync + mouth-shape accuracy > Stable identities across long videos & multi-person scenes > Smooth full-body motion, singing, animation, & hand interactions > Outperforms HeyGen, Kling Avatar 2.0, & OmniHuman-1.5 in consistency tests Free & open source

⚡AI Search⚡

12,505 просмотров • 24 дней назад

We will be in ACM SIGGRAPH 2023 with "3D Gaussian Splatting for Real-Time Radiance Field Rendering", have you ever seen radiance fields with 100+ FPS and MipNeRF360 quality? Check out our website here:
0:14

We will be in ACM SIGGRAPH 2023 with "3D Gaussian Splatting for Real-Time Radiance Field Rendering", have you ever seen radiance fields with 100+ FPS and MipNeRF360 quality? Check out our website here:

George Kopanas

135,782 просмотров • 3 лет назад

Rare high view of the building left over from a previous simulation that humans here did not build and has false documentation of its "632 year" construction to cover its tracks so no one realizes it. In my humble opinion of course.
0:17

Rare high view of the building left over from a previous simulation that humans here did not build and has false documentation of its "632 year" construction to cover its tracks so no one realizes it. In my humble opinion of course.

Invisidon

294,704 просмотров • 4 месяцев назад

We just streamed the first ultra-HD video brought to you via laser from deep space. And it’s a video of Taters, a tabby cat. This test will pave the way for high-data-rate communications in support of the next giant leap: sending humans to Mars.
0:15

We just streamed the first ultra-HD video brought to you via laser from deep space. And it’s a video of Taters, a tabby cat. This test will pave the way for high-data-rate communications in support of the next giant leap: sending humans to Mars.

NASA

1,967,222 просмотров • 2 лет назад

This is RICULOUSLY good, TRELLIS 3D Generation model by Microsoft! 🔥 Generate high-quality 3D assets from text or image prompts. Supports various formats like Radiance Fields, 3D Gaussians, and meshes Available for FREE on Hugging Face!
0:14

This is RICULOUSLY good, TRELLIS 3D Generation model by Microsoft! 🔥 Generate high-quality 3D assets from text or image prompts. Supports various formats like Radiance Fields, 3D Gaussians, and meshes Available for FREE on Hugging Face!

Vaibhav (VB) Srivastav

62,437 просмотров • 1 год назад

Quality of life improves when you listen to birds more than you do humans
0:15

Quality of life improves when you listen to birds more than you do humans

Jelena

26,625 просмотров • 1 месяц назад

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.
0:18

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

AK

633,313 просмотров • 2 лет назад

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.
0:10

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

MrNeRF

24,729 просмотров • 11 месяцев назад