image-to-3d

A user tested image-to-3D model Seed3D 2.0 via Atlas Cloud on a single photo of a fire hydrant, finding that the reconstructed back and overall shape looked convincing, but fine details like raised cast lettering were completely missing from the mesh—highlighting how AI 3D demos can appear plausible while losing object-specific fidelity.

NVIDIA开源了名为Lyra 2.0的模型，可将任意单张图片直接转换为可自由探索的交互式3D世界，甚至可用于向生成的场景中放入机器人进行仿真训练。模型已发布到Hugging Face，UI代码也已在GitHub开源。

A viral post claims that a GitHub repository can turn any single photo into a fully explorable 3D world — complete with physics-enabled meshes, background splats, and ambient audio — within minutes, shaking up an entire industry of 3D content creation.

A tweet hypes a new open-source GitHub repository called image-blaster that turns a single photo into an explorable 3D world — complete with meshes, physics effects, background splats, and environmental audio — claiming the tool could disrupt traditional 3D modeling workflows.

OctLLM represents 3D geometry as explicit SparseOctree occupancy tokens and routes mesh tokens through independent trainable branches alongside a frozen vision-language backbone, setting a new state of the art among unified multimodal LLMs for image-to-3D and render-grounded captioning while preserving general language ability.

World Labs introduces Atlas, an AI model trained on NVIDIA Blackwell GPUs that generates real-time 3D views from 32 input images, enabling pixel-perfect camera control for exploration.

Luce unifies geometry and PBR materials in a voxelized Gaussian cloud to generate relightable 3D assets from single images, achieving state-of-the-art results on benchmarks like Toys4K.

Introducing the open-source project img2threejs on GitHub. Upload an ordinary photo and it automatically generates a code-based Three.js 3D model with hierarchy and collision bodies, suitable for direct use by developers and game creators.

This is an open-source 3D model generation project that can generate detailed 3D models from images, such as CS2 butterfly knife and Sony camera, with realistic results.

img2threejs v1.3 is a tool that converts a single photo into procedural Three.js code without meshes or manual modeling, with major improvements to geometry reconstruction and material generation.

Introduces a new open-source toolkit, img2threejs, that converts photos into Three.js models and automatically compares the rendering result with the original image to calibrate reconstruction quality, especially suitable for hard-surface objects.

A new model enables generating 3D models from a single image locally on Apple Silicon devices and iPhones, using less than 2GB RAM and completing in under 20 seconds.

SynCity 3000 introduces a framework for generating large, globally coherent 3D scenes by adapting image-to-3D generators as convolutional operators, fine-tuned on synthetic scene data from a new data engine.

This article covers how to run Hunyuan3D, an AI model that converts images to 3D objects, directly on an iPhone.

FLUX3D introduces a framework for high-fidelity image-to-3D Gaussian Splatting generation by enhancing representation learning and cross-modal alignment with diffusion-aligned structured latents and a sparse-structure-aware diffusion transformer, achieving state-of-the-art results.

World Tracing introduces a generative pixel-aligned geometry representation that predicts 3D points aligned with observed pixels while completing occluded surfaces. It uses a diffusion transformer trained with pixel-space flow matching, achieving strong performance on visible-surface reconstruction and complete geometry generation across object, scene, and dynamic benchmarks.

A new 3D AI generator can take any image and produce high-polygon 3D models with up to 10 million polygons and skin microstructures.

A new AI model can generate modular Unreal Engine 5 environments from a single input image, enabling rapid 3D scene creation.

OpenArt now allows users to transform a single image into a persistent 3D world with precise camera control, powered by the World Labs API.

Microsoft released a 4B parameter model that converts any image into a 3D asset in 3 seconds, using the O-Voxel geometry format and outputting GLB files with full PBR textures, compatible with Blender, Unity, and Unreal.