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。

C++ code is out! The Signed Heat Method has been added to geometry-central. In 3D, compute generalized SDFs to point clouds, triangle meshes, and polygon meshes. The method should "just work" on geometry with holes, intersections, nonmanifold-ness, etc. Links below 🔽

Nicole Feng

1,552 subscribers

56,854 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

Nicole Feng 的头像

Nicole Feng1 年前

Demo projects here: The demo projects let you try things out right away: load your own data, play around with constraints, export solutions. I also included a Blender file with the shader I used to make our paper figures. Enjoy!

Nicole Feng 的头像

Nicole Feng1 年前

Main X thread here: Paper and project here:

Nicole Feng 的头像

Nicole Feng1 年前

FYI shoutout to Chris Yu and Nick Sharp (@nmwsharp) for developing the awesome volume grid/tet visualization features in Polyscope.

Hayden 的头像

Hayden1 年前

sick

Hugo Elias 的头像

Hugo Elias1 年前

very cool, I love the idea & the paper! SDFs 💞

Dan Brickley 的头像

Dan Brickley1 年前

Do the point cloud methods make sense for 3D Gaussian splats?

Nicole Feng 的头像

Nicole Feng1 年前

Haven't tried gaussian splats, but in principle the method should work as you have normals for the geometry - which for gaussians might be done by taking a gradient where you've deemed your zero level set surface to be. Might be some finicky details to figure out.

Ronal Dragon 的头像

Ronal Dragon1 年前

incredible! I'll see if I can replace CGAL's AlphaWrap with it (for offset surfaces)

Kiaran Ritchie 的头像

Kiaran Ritchie1 年前

Amazing. I could use this.

木十的头像

木十1 年前

wow

相关视频

Nvidia presents EdgeRunner! The method can generate high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 from images and point-clouds.

Nvidia presents EdgeRunner! The method can generate high-quality 3D meshes with up to 4,000 faces at a spatial resolution of 512 from images and point-clouds.

Dreaming Tulpa 🥓👑

173,103 次观看 • 1 年前

Super clean and efficient meshes by an AI? YES! The typical 3D Generative AI solutions produce lots of artifacts and usually way to many polygons due to volumetric approaches. In comparison “MeshGPT creates triangle meshes by autoregressively sampling from a transformer model that has been trained to produce tokens from a learned geometric vocabulary. These tokens can then be decoded into the faces of a triangle mesh. This method generates clean, coherent, and compact meshes, characterized by sharp edges and high fidelity.” Surely it is limited by the trained vocabulary but various versions can be trained for specific sets to create generative model libraries for certain object groups. Very promising approach with the high quality.

Super clean and efficient meshes by an AI? YES! The typical 3D Generative AI solutions produce lots of artifacts and usually way to many polygons due to volumetric approaches. In comparison “MeshGPT creates triangle meshes by autoregressively sampling from a transformer model that has been trained to produce tokens from a learned geometric vocabulary. These tokens can then be decoded into the faces of a triangle mesh. This method generates clean, coherent, and compact meshes, characterized by sharp edges and high fidelity.” Surely it is limited by the trained vocabulary but various versions can be trained for specific sets to create generative model libraries for certain object groups. Very promising approach with the high quality.

René Schulte

20,772 次观看 • 2 年前

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 次观看 • 2 年前

🔥 HUGE: Today, we are thrilled to unveil a massive breakthrough in AI and 3D: ✨Introducing Primfusion v0 💫 For the first time ever in 3D, easily convert your 3D meshes, scans, and high-poly models into easy-to-edit, goopy primitives in Womp. Trained solely on geometry principles, never your style. Join the waitlist ➡️ Questions/Concerns? Check out our FAQ ➡️ #womp3d #3dmodeling

🔥 HUGE: Today, we are thrilled to unveil a massive breakthrough in AI and 3D: ✨Introducing Primfusion v0 💫 For the first time ever in 3D, easily convert your 3D meshes, scans, and high-poly models into easy-to-edit, goopy primitives in Womp. Trained solely on geometry principles, never your style. Join the waitlist ➡️ Questions/Concerns? Check out our FAQ ➡️ #womp3d #3dmodeling

Womp

136,265 次观看 • 2 年前

DeepMesh is out on Hugging Face Auto-Regressive Artist-mesh Creation with Reinforcement Learning Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality.

DeepMesh is out on Hugging Face Auto-Regressive Artist-mesh Creation with Reinforcement Learning Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality.

AK

109,201 次观看 • 1 年前

To support massive, high-fidelity worlds, our engine implements an efficient LOD strategy with a cloud transcoding system that streams meshes and textures, even on lower end mobile devices. We are expanding this framework to AI upsampling of 3D worlds from prompts. In this preview video below, with a single user prompt, our 3D upsampling technology updates the geometry and texture to transform the classic Roblox game Crossroads into a fantasy world with rich organic detail. 3/4

To support massive, high-fidelity worlds, our engine implements an efficient LOD strategy with a cloud transcoding system that streams meshes and textures, even on lower end mobile devices. We are expanding this framework to AI upsampling of 3D worlds from prompts. In this preview video below, with a single user prompt, our 3D upsampling technology updates the geometry and texture to transform the classic Roblox game Crossroads into a fantasy world with rich organic detail. 3/4

Roblox

1,421,694 次观看 • 5 个月前

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

Abdullah Hamdi

71,661 次观看 • 1 年前

Curve hair, but you can set different meshes per curve strand! And have options to adjust them. And its using the flat wrapping method so its easy to work with! This is the hair workflow i've wanted for over 7 years, and it can finally be built #b3d

Curve hair, but you can set different meshes per curve strand! And have options to adjust them. And its using the flat wrapping method so its easy to work with! This is the hair workflow i've wanted for over 7 years, and it can finally be built #b3d

aVersionOfReality

147,949 次观看 • 3 年前

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 次观看 • 3 个月前

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

Gabriele Romagnoli

2,177,047 次观看 • 1 年前

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion discuss: We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry, appearance, and patch structures within a 64x64 pixel image, effectively converting complex 3D shapes into a more manageable 2D format. By doing so, we address the challenges of both geometric and semantic irregularity inherent in polygonal meshes. This method allows us to use image generation models, such as Diffusion Transformers, directly for 3D shape generation. Evaluated on the ABO dataset, our generated shapes with patch structures achieve point cloud FID comparable to recent 3D generative models, while naturally supporting PBR material generation.

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion discuss: We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry, appearance, and patch structures within a 64x64 pixel image, effectively converting complex 3D shapes into a more manageable 2D format. By doing so, we address the challenges of both geometric and semantic irregularity inherent in polygonal meshes. This method allows us to use image generation models, such as Diffusion Transformers, directly for 3D shape generation. Evaluated on the ABO dataset, our generated shapes with patch structures achieve point cloud FID comparable to recent 3D generative models, while naturally supporting PBR material generation.

AK

66,486 次观看 • 2 年前

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Unreal Engine asset packs are about to be worthless. Tencent just shipped HY-World 2.0. You type one sentence. It outputs a real 3D scene with meshes, point clouds, and 3DGS that drags straight into your game engine. Renders in real time on a consumer GPU. Phone video in, digital twin out, one forward pass. The marketplace economy of selling 3D assets just had its Napster moment.

Ihtesham Ali

45,956 次观看 • 2 个月前

🦊Fara Rex V3 Mod is out! - Updated to 1.5 Rex - Quest Compatible - Reduced triangle count - Improved crotch weight and geometry - Body fluff - Corrective blend shapes Get it for FREE on the Rexouium Discord! Links and more on my Gumroad page

🦊Fara Rex V3 Mod is out! - Updated to 1.5 Rex - Quest Compatible - Reduced triangle count - Improved crotch weight and geometry - Body fluff - Corrective blend shapes Get it for FREE on the Rexouium Discord! Links and more on my Gumroad page

Fara \\ FWA

35,290 次观看 • 3 年前

Thrilled to share our new work on Reconviagen✨! A key challenge in 3D creation is the alignment of generative 3D with observational input. Our method solves this by grounding the generative process in 3D reconstruction. Try it at: #Reconstruction #AIGC

Thrilled to share our new work on Reconviagen✨! A key challenge in 3D creation is the alignment of generative 3D with observational input. Our method solves this by grounding the generative process in 3D reconstruction. Try it at: #Reconstruction #AIGC

Chongjie Ye

11,624 次观看 • 11 个月前

"Generate in Parts" just got better with "Split in Parts"! 🥹😇 Hervé Nivon added a toggle in the Scenario 3D viewer that instantly splits generated meshes into an exploded view. See how PartCrafted breaks down your model - no need to download and check in Blender anymore.

"Generate in Parts" just got better with "Split in Parts"! 🥹😇 Hervé Nivon added a toggle in the Scenario 3D viewer that instantly splits generated meshes into an exploded view. See how PartCrafted breaks down your model - no need to download and check in Blender anymore.

Emm | scenario.com

16,492 次观看 • 1 年前

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 次观看 • 3 年前

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

MrNeRF

27,277 次观看 • 1 年前

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Large-scale 3D Scene Generation (all scenes are real-time rendered)!! Physically-grounded generative data without hallucinations is the missing link for robot learning and testing at scale. We introduce a method that directly generates large-scale 3D driving scenes with accurate geometry, allowing for causal view synthesis and generation with object permanence and explicit 3D geometry. This also allows for extreme trajectory extrapolation without failure! We also show that we can build fully data-driven simulators for end-to-end learning with this approach. Project: with the amazing team of Julian Ost, Amogh Joshi , Andrea Ramazzina, Maximilian Bömer, Mario Bijelic.

Felix Heide

27,779 次观看 • 11 个月前

More glass shattering adventures #screenshotsaturday I went with a less flashy method that performs better. I am tempted to try using a compute shader to make the previous one viable. Then again I should get to some actual gameplay and this has already been an insane ordeal.

More glass shattering adventures #screenshotsaturday I went with a less flashy method that performs better. I am tempted to try using a compute shader to make the previous one viable. Then again I should get to some actual gameplay and this has already been an insane ordeal.

Damian

34,062 次观看 • 1 年前