In traditional 3D modeling, the process often begins with a concept sketch or a 2D image. Designers then have to manually interpret these flat visuals and reconstruct them in a 3D environment.

Specifically, MonoCon is capable of identifying 3D objects in 2D images and placing them in a "bounding box," which effectively tells the AI the outermost edges of the relevant object.

The software is designed to create 3D objects from scratch using 2D images as the input. It uses AI to evaluate the 2D image and constructs a mesh from the data.

[Carson Katri] has a fantastic solution to easily add textures to 3D scenes in Blender: have an image-generating AI create the texture on demand, and do it for you. As shown here, two featureless b… ...

An AI method enables the generation of sharp, high-quality 3D shapes that are closer to the quality of the best 2D image models. Previous approaches typically generated blurry or cartoonish 3D shapes.

Nvidia on Tuesday is debuting new research into 3D rendering that could one day make it easier for graphic artists, architects, and other creators to quickly build 3D models out of 2D images.

Mice can recognise 3D objects from memory of their 2D photos, study suggests ‘Picture-to-object equivalence’ has long been thought to be a cognitive function beyond rodents’ abilities ...

NVIDIA explains that early NeRF models don't take too long to produce results either. It only takes them a few minutes to render a 3D scene, even if the subject in some of the images is obstructed ...

From 2D images to 3D shapes. Diffusion models, such as DALL-E, are a type of generative AI model that can produce lifelike images from random noise. To train these models, ...