The technology, known as Score Distillation Sampling, uses models to create 2D images and transform them into 3D shapes. However, this process has often previously produced ambiguous results due to limitations in AI training. MIT investigated the reasons for this phenomenon and found a simple solution that improves the quality of 3D objects.
Scientists have achieved clearer, more realistic 3D shapes by replacing the random noise used in the conversion process with more accurate approximations. The quality of the models has been further increased, and the machining details have also been improved.
The MIT method does not require additional costs for retraining AI models, making it more cost-effective than other solutions. It also opens up new possibilities for creating 3D objects in fields such as virtual reality and filmmaking.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
