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.

Apple drops a new 3D model generator, LiTo > Learns geometry + appearance together in a unified 3D latent space > Turns RGB-D images into a compact surface light field > Recreates specular highlights under complex lighting > Generates 3D objects from a single image with input-consistent materials Big... show more

AI Search

24,713 subscribers

13,078 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 Comments

🇺🇦 S☽M ☥5 months ago

@artificialguybr Check this: if the demos are realistic results, without tinkering, it's another level.

Entropy Hertz5 months ago

@bdsqlsz @grok can I mod Skyrim with this?

Related Videos

LiTo: Surface Light Field Tokenization (ICLR 2026) — new work from Apple MLR. LiTo learns a unified 3D representation of geometry + view-dependent appearance, capturing effects like specular highlights & Fresnel reflections, enabling high-fidelity 3D generation from single image.

LiTo: Surface Light Field Tokenization (ICLR 2026) — new work from Apple MLR. LiTo learns a unified 3D representation of geometry + view-dependent appearance, capturing effects like specular highlights & Fresnel reflections, enabling high-fidelity 3D generation from single image.

Oncel Tuzel

43,377 views • 7 months ago

Apple’s new LiTo model showcases a new method of converting 2D images to highly realistic 3D (Gaussian splat) objects More interestingly: it aims to accurately mimic the complex lighting, materials, and reflections shown in the original photo! They’re working to open source it

Apple’s new LiTo model showcases a new method of converting 2D images to highly realistic 3D (Gaussian splat) objects More interestingly: it aims to accurately mimic the complex lighting, materials, and reflections shown in the original photo! They’re working to open source it

Brad Lynch

40,615 views • 7 months ago

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

0xMarioNawfal

47,656 views • 3 months ago

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 views • 2 years ago

Tencent ARC releases GAE: a geometry-native latent space for 3D-consistent world generation GAE compresses 3,072-channel geometry features into a compact 128-channel latent that decodes into RGB, depth, camera trajectories, and point clouds from the same generated state. It halves camera-trajectory error and cuts FVD by up to 23% on standard benchmarks.

Tencent ARC releases GAE: a geometry-native latent space for 3D-consistent world generation GAE compresses 3,072-channel geometry features into a compact 128-channel latent that decodes into RGB, depth, camera trajectories, and point clouds from the same generated state. It halves camera-trajectory error and cuts FVD by up to 23% on standard benchmarks.

DailyPapers

25,488 views • 1 month ago

Meshy V7.1 is now live on fal. Turn an idea into a production-ready 3D asset from text or images. - Generate 3D models from text or image prompts - Combine multiple reference views into a single, coherent model - Generate textured assets with PBR maps for realistic materials and lighting Build with Meshy V7.1 on fal.

Meshy V7.1 is now live on fal. Turn an idea into a production-ready 3D asset from text or images. - Generate 3D models from text or image prompts - Combine multiple reference views into a single, coherent model - Generate textured assets with PBR maps for realistic materials and lighting Build with Meshy V7.1 on fal.

fal

23,984 views • 1 month ago

🚀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 views • 1 year ago

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 views • 11 months ago

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.

Alexandre Morgand

15,192 views • 8 months ago

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

66,852 views • 2 years ago

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 views • 3 years ago

whats interesting is you can "trick" Atlas into becoming a 3D modeling tool by placing input images in 3D space the model then creates a coherent world this is how this scene was made – all the model sees is camera pose + RGB

whats interesting is you can "trick" Atlas into becoming a 3D modeling tool by placing input images in 3D space the model then creates a coherent world this is how this scene was made – all the model sees is camera pose + RGB

neilson

58,017 views • 2 months ago

Making 3D assets just got stupidly easy. Tripo turns a sentence or a single image into a full 3d model, ready for blender, games, printing, whatever. Idea → image → 3D asset. Full workflow below 🧵

Making 3D assets just got stupidly easy. Tripo turns a sentence or a single image into a full 3d model, ready for blender, games, printing, whatever. Idea → image → 3D asset. Full workflow below 🧵

Farhan

44,468 views • 4 months ago

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that directly generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

126,142 views • 1 year ago

📢 Matrix-3D: Omnidirectional 3D World Generation Ever wanted to turn a single image or a text prompt into a massive, explorable 3D world? That’s exactly what Matrix-3D does.

📢 Matrix-3D: Omnidirectional 3D World Generation Ever wanted to turn a single image or a text prompt into a massive, explorable 3D world? That’s exactly what Matrix-3D does.

Skywork

30,417 views • 1 year ago