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。

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

1,980 subscribers

53,252 次观看 • 1 年前 •via X (Twitter)

科学技术艺术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Yuan Liu 的头像

Yuan Liu1 年前

The key idea is to adopt the multiview diffusion to generate novel-view images and normal maps. Then, we apply inverse rendering techniques to reconstruct the textured human meshes. We improve face reconstruction with a global-local denoising scheme.

jason rugolo 的头像

jason rugolo1 年前

incredible work

Roman 的头像

Roman1 年前

Great! I tried to replicate my wife in blender modifying a human model, now i suppose i'd just have to take a pic of her in A-pose, use PSHuman then add bones/rig in blender? 😃

Ulysse Mizrahi 的头像

Ulysse Mizrahi1 年前

What's the novelty compared to any image to mesh techniques which exist today? Also I'm seeing a bunch of seam artifacts on the textures

Yuan Liu 的头像

Yuan Liu1 年前

We add SMPL skeletons to guide the diffusion process, generate 6 novel-view images, and improve the face regions with a new denoiser. The multiview-to-mesh reconstruction follows Unique3D but initializes from SMPL.

Turbotardo 的头像

Turbotardo1 年前

Now do that for cats please

Hector 的头像

Hector1 年前

can this be ported to say fbx format? say unreal engine's metahuman face and body?

Yuan Liu 的头像

Yuan Liu1 年前

We are not so familiar with UE and probably cannot support it. This may not be directly applicable to Game development, which still requires additional efforts in remeshing, animation, etc.😊

Synthical 的头像

Synthical1 年前

Dark mode for this paper 🌚

XJournalK 的头像

XJournalK1 年前

Anywhere a user can try?

相关视频

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

79,751 次观看 • 2 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 • 21 天前

🚀Exicited to present our new work "InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars". Given single or more source images, our method rapidly reconstructs photorealistic 3D facial avatars under 1s. Paper: Project page comes soon!

🚀Exicited to present our new work "InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars". Given single or more source images, our method rapidly reconstructs photorealistic 3D facial avatars under 1s. Paper: Project page comes soon!

Jingxiang Sun

16,742 次观看 • 2 年前

Excited to share our recent work, UniSH, which unifies dynamic 3D scene reconstruction and SMPL estimation within a single framework. (Left-top is input video). Code has been released! Project page: Paper:

Excited to share our recent work, UniSH, which unifies dynamic 3D scene reconstruction and SMPL estimation within a single framework. (Left-top is input video). Code has been released! Project page: Paper:

Yuan Liu

19,258 次观看 • 9 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

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 次观看 • 1 年前

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds

Dreaming Tulpa 🥓👑

21,853 次观看 • 1 年前

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 次观看 • 3 年前

🏗️ Build #3D scenes from a single input view based on the latest #NVIDIAResearch paper accepted at #ICCV2023. 👀 This 3D-aware #generativeAI model can build diverse and plausible views. research paper: project page:

🏗️ Build #3D scenes from a single input view based on the latest #NVIDIAResearch paper accepted at #ICCV2023. 👀 This 3D-aware #generativeAI model can build diverse and plausible views. research paper: project page:

NVIDIA AI Developer

113,954 次观看 • 3 年前

Meet our new and fast 3D sculpting model! ✅ Single image to mesh with detailed geometry in the order of minutes (more GPUs coming to get to <30-60s) ✅ Dense mesh re-topology using our custom language model (minutes) Available on all Cube plans:

Meet our new and fast 3D sculpting model! ✅ Single image to mesh with detailed geometry in the order of minutes (more GPUs coming to get to <30-60s) ✅ Dense mesh re-topology using our custom language model (minutes) Available on all Cube plans:

Common Sense Machines

53,311 次观看 • 2 年前

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Nature presents a captivating confluence of similarity and diversity. Our new method 3D-Fauna learns a pan-category articulated 3D model of quadruped animals from Internet photos. At test time, it turns a single image into an animatable textured 3D mesh in a feed-forward pass.

Elliott / Shangzhe Wu

107,391 次观看 • 2 年前

Excited to share our #CVPR2023 on synthesizing new views along a camera trajectory from a **single image**! How? 💡 The good old epipolar constraints in a pose-guided diffusion model! Paper: Project:

Excited to share our #CVPR2023 on synthesizing new views along a camera trajectory from a single image! How? 💡 The good old epipolar constraints in a pose-guided diffusion model! Paper: Project:

Jia-Bin Huang

94,199 次观看 • 3 年前

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Stan Szymanowicz

26,994 次观看 • 1 年前

Excited to share Track4World, feedforward 3D tracking of all pixels in the world-centric coordinate system. Code has been released, and welcome to try it! Homepage: Code: Paper:

Excited to share Track4World, feedforward 3D tracking of all pixels in the world-centric coordinate system. Code has been released, and welcome to try it! Homepage: Code: Paper:

Yuan Liu

20,337 次观看 • 8 个月前

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.

three.ws

34,487 次观看 • 4 个月前

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,734 次观看 • 2 个月前

I'm excited to share our new work Align3R that estimates camera poses and consistent depth maps from a monocular video of a dynamic scene. Project page: Code: Paper:

I'm excited to share our new work Align3R that estimates camera poses and consistent depth maps from a monocular video of a dynamic scene. Project page: Code: Paper:

Yuan Liu

56,547 次观看 • 1 年前