正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We released our ActorsHQ dataset from our #SIGGRAPH work: "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion". ActorsHQ provides high-fidelity multi-view captures at 12MP resolution from 160 cameras with per-frame mesh reconstructions.

Matthias Niessner

50,691 subscribers

22,756 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 条评论

Matthias Niessner 的头像

Matthias Niessner3 年前

This is work by @synthesiaIO Research, lead by @realMustafaIsik, @martin_ruenz, Markos, @t_khakhulin, @jnstrck, @LourdesAgapito. Our aim is to support super exciting research towards photo-realistic human avatars! Also check out the #SIGGRAPH2023 paper:

AssemblyAI 的头像

AssemblyAI2 年前

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

kfant 的头像

kfant3 年前

i have similar setup at home although with 256 cameras , very PRACTICAL!🤪

相关视频

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

AK

160,723 次观看 • 3 年前

Sharing our new work: UniForge3D generates detailed 3D meshes from sparse-view inputs with high fidelity! The code has been released and welcome to try it! Paper: Project Page: Code:

Sharing our new work: UniForge3D generates detailed 3D meshes from sparse-view inputs with high fidelity! The code has been released and welcome to try it! Paper: Project Page: Code:

Yuan Liu

29,511 次观看 • 16 天前

Meta presents: Pippo : High-Resolution Multi-View Humans from a Single Image Generates 1K resolution, multi-view, studio-quality images from a single photo in a one forward pass

Meta presents: Pippo : High-Resolution Multi-View Humans from a Single Image Generates 1K resolution, multi-view, studio-quality images from a single photo in a one forward pass

Aran Komatsuzaki

32,588 次观看 • 1 年前

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

(1/2) 📢📢📢NeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

Matthias Niessner

69,702 次观看 • 3 年前

Upload single or multi-view images to ComfyUI’s HY 3D 3.0 nodes for high-fidelity 3D assets—from product displays to game dev, done in minutes!

Upload single or multi-view images to ComfyUI’s HY 3D 3.0 nodes for high-fidelity 3D assets—from product displays to game dev, done in minutes!

ComfyUI

25,687 次观看 • 6 个月前

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

ByteDance just announced MagicVideo-V2 Multi-Stage High-Aesthetic Video Generation paper page: The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika 1.0, Morph, Moon Valley and Stable Video Diffusion model via user evaluation at large scale

AK

181,049 次观看 • 2 年前

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

Chen-Hsuan Lin

253,392 次观看 • 3 年前

Live from Apsara Conference 2026, an immersive, multi-screen look at where AI meets creativity. Watch how our models are multimodal generation, from high-fidelity image and audio synthesis to seamless cinematic video and interactive virtual worlds.

Live from Apsara Conference 2026, an immersive, multi-screen look at where AI meets creativity. Watch how our models are multimodal generation, from high-fidelity image and audio synthesis to seamless cinematic video and interactive virtual worlds.

Alibaba Group

2,113,204 次观看 • 1 个月前

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.

Matthias Niessner

16,975 次观看 • 2 年前

LUCRO SUCIO; UNFINISHED BUSINESS is here. We've taken an experimental approach with this record, combining live performances from our recent tour into a high-fidelity, multi-layered reimagining of Lucro Sucio. Pre-order here:

LUCRO SUCIO; UNFINISHED BUSINESS is here. We've taken an experimental approach with this record, combining live performances from our recent tour into a high-fidelity, multi-layered reimagining of Lucro Sucio. Pre-order here:

THE MARS VOLTA

17,339 次观看 • 4 个月前

UX/UI timelapse from wireframe to final high-fidelity design

UX/UI timelapse from wireframe to final high-fidelity design

Jan Mraz

39,081 次观看 • 1 年前

Just 1,500 feet (457 m) from the Artemis II launch, we deployed our special high-resolution, slow-motion camera to record the blast-off in jaw-dropping detail at 2,000 frames per second. Find out how we did it:

Just 1,500 feet (457 m) from the Artemis II launch, we deployed our special high-resolution, slow-motion camera to record the blast-off in jaw-dropping detail at 2,000 frames per second. Find out how we did it:

National Geographic

314,844 次观看 • 7 个月前

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:

Angela Dai

14,702 次观看 • 11 个月前

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 次观看 • 3 年前

1979 High Fidelity.

1979 High Fidelity.

Brian Roemmele

420,421 次观看 • 6 个月前

HiFi-UMI Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone paper:

HiFi-UMI Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone paper:

AK

52,851 次观看 • 3 个月前

Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior abs: project page:

Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior abs: project page:

AK

163,868 次观看 • 3 年前

LUNA: Universal 3D human animation via LBS-free mapping - driving from images, sketches, keypoints - 3DGS + Sapiens for high-fidelity cross-identity animation - low temporal jitter - captures loose clothing dynamics

LUNA: Universal 3D human animation via LBS-free mapping - driving from images, sketches, keypoints - 3DGS + Sapiens for high-fidelity cross-identity animation - low temporal jitter - captures loose clothing dynamics

Wildminder

25,606 次观看 • 4 个月前