Adobe and Australian National University Unveil Breakthrough: AI Generates 3D Images from 2D in Seconds

Date:

Adobe and the Australian National University (ANU) have made a groundbreaking announcement in the field of 3D visualizations. They have unveiled the first artificial intelligence (AI) model capable of generating 3D images from a single 2D image. This development is set to transform the creation of 3D models, as the algorithm developed by the researchers can generate these images in a matter of seconds.

The AI model, known as the large reconstruction model (LRM), is based on a highly scalable neural network containing one million datasets with 500 million parameters. These datasets include images, 3D shapes, and videos. The combination of this high-capacity model and large-scale training data enables the model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs.

According to Yicong Hong, the lead author of the project report and an Adobe intern and former graduate student at ANU, their LRM is the first large-scale 3D reconstruction model. This breakthrough technology is expected to have wide-ranging applications in augmented reality and virtual reality systems, gaming, cinematic animation, and industrial design.

Previously, 3D imaging software was limited to specific subject categories with pre-established shapes. Later advancements in image generation were achieved with programs like DALL-E and Stable Diffusion, which leveraged the generalization capability of 2D diffusion models for multi-views. However, these programs were limited to pre-trained 2D generative models. Other systems utilized per-shape optimization, but they were often slow and impractical.

Inspired by the evolution of natural language models within massive transformer networks, Hong’s team asked if it was possible to learn a generic 3D prior for reconstructing an object from a single image. Their answer was a resounding yes. The LRM can reconstruct high-fidelity 3D shapes from various real-world images and those created by generative models. It can produce a 3D shape in just five seconds without the need for post-optimization.

See also  Tesla's Dojo Supercomputer Could Power $600B Surge in Market Value - Morgan Stanley, US

The success of the LRM lies in its ability to draw upon a vast database of image parameters and predict a neural radiance field (NeRF), which allows for the generation of realistic-looking 3D imagery based solely on 2D pictures, even low-resolution ones. NeRF encompasses image synthesis, object detection, and image segmentation capabilities.

It has been 60 years since the first computer program that allowed users to generate and manipulate simple 3D shapes was created. Over the decades, 3D programs have seen remarkable advancements. Now, with Adobe and ANU’s breakthrough, the field of 3D visualizations is set to be revolutionized once again.

References:
– Adobe and Australian National University Unveil Breakthrough: AI Generates 3D Images from 2D in Seconds [Article Link]

Frequently Asked Questions (FAQs) Related to the Above News

What is the groundbreaking announcement made by Adobe and the Australian National University (ANU)?

Adobe and ANU have unveiled the first AI model capable of generating 3D images from a single 2D image.

What is the name of the AI model developed by the researchers?

The AI model is called the large reconstruction model (LRM).

How is the LRM different from previous 3D imaging software?

The LRM is different because it can generate high-quality 3D reconstructions from various testing inputs in a matter of seconds, whereas previous software had limitations in terms of subject categories and were often slow.

How does the LRM reconstruct 3D shapes from 2D images?

The LRM utilizes a vast database of image parameters and predicts a neural radiance field (NeRF), allowing for the generation of realistic-looking 3D imagery based solely on 2D pictures.

What are some potential applications of this groundbreaking technology?

This technology has wide-ranging applications in augmented reality and virtual reality systems, gaming, cinematic animation, and industrial design.

How long does it take for the LRM to produce a 3D shape?

The LRM can produce a 3D shape in just five seconds without the need for post-optimization.

What sets the LRM apart from previous generative models?

The LRM is the first large-scale 3D reconstruction model and can reconstruct high-fidelity 3D shapes from various real-world images and generative models.

How does the LRM contribute to the field of 3D visualizations?

The LRM revolutionizes 3D visualizations by enabling the generation of high-quality 3D images from single 2D images, significantly transforming the creation of 3D models.

What is a neural radiance field (NeRF)?

A neural radiance field (NeRF) is a concept that allows for the generation of realistic-looking 3D imagery by predicting a volumetric scene representation based on a collection of 2D images.

What is the potential impact of this breakthrough in the field of 3D visualizations?

This breakthrough in AI-generated 3D images has the potential to revolutionize various industries, including augmented reality, virtual reality, gaming, animation, and industrial design, by enabling faster and more realistic 3D model creation.

Please note that the FAQs provided on this page are based on the news article published. While we strive to provide accurate and up-to-date information, it is always recommended to consult relevant authorities or professionals before making any decisions or taking action based on the FAQs or the news article.

Share post:

Subscribe

Popular

More like this
Related

UK Regulator Probes Microsoft’s Control over OpenAI in AI Market Antitrust Inquiry

UK regulator investigates Microsoft's control over OpenAI in AI market antitrust inquiry. Concerns raised about partnership, potential impact on competition. Microsoft emphasizes independence while cooperating with inquiry. Outcome to determine control and innovation in AI market.

Google Introduces Gemini AI, Challenging ChatGPT’s Dominance

Google introduces Gemini AI, challenging ChatGPT's dominance. This revolutionary multimodal model outperforms GPT-4, reshaping the AI landscape.

Google Infuses Bard AI Chatbot with New AI Model Gemini, Promising Superior Reasoning, Australia

Google's AI chatbot, Bard, is being enhanced with a new AI model called Gemini, promising superior reasoning abilities. This comes in response to a growing number of takedown requests related to harmful or incorrect information from AI technology like Bard, highlighting the need for targeted solutions like machine unlearning. While some experts prioritize teaching algorithms to forget specific data, others focus on faster learning and more efficient fact retrieval. The industry continues to debate the significance of machine unlearning in addressing the challenges of misinformation and harmful content.

Albanian PM Taps AI Expert to Harmonize Laws with EU

Albanian PM partners with AI expert to harmonize laws with EU, saving millions. Groundbreaking collaboration uses AI technology to streamline process.