A new #generativeai app that lets you create surprisingly coherent compositions with a unique & delightful 3D interface. Early access!
By @ayssar + @makerbrane
Today we're launching https://t.co/mwQwUDeYsl - the lightweight 3D Ai studio for quickly generating design ideas (and mood boards) from your 3D models from anywhere, including your mobile. What kind of design? Everything #3d, here's a breakdown in the thread:
@skirano@everartai I'm mostly interested in being able to train on a particular building and let the AI render it in different image styles without changing the architecture itself. is that possible?
@fernandorojo@ddaalee jumping in... confused by the docs - it looks different from the create-solito-app@latest version. For example https://t.co/SmQLCgd8DR vs https://t.co/dSqr4L9CmI... which is the right approach?
Hey @fernandorojo!
Excited about Solito but I have zero experience with React Native. I'm trying to make a mobile version of a NextJS webapp. Do i have to transform all my NextJS/chakra-ui components into React Native, and THEN add the Solito components? any beginner pointers?
CityDreamer: Compositional Generative Model of Unbounded 3D Cities
paper page: https://t.co/28KYlR80Pc
In recent years, extensive research has focused on 3D natural scene generation, but the domain of 3D city generation has not received as much exploration. This is due to the greater challenges posed by 3D city generation, mainly because humans are more sensitive to structural distortions in urban environments. Additionally, generating 3D cities is more complex than 3D natural scenes since buildings, as objects of the same class, exhibit a wider range of appearances compared to the relatively consistent appearance of objects like trees in natural scenes. To address these challenges, we propose CityDreamer, a compositional generative model designed specifically for unbounded 3D cities, which separates the generation of building instances from other background objects, such as roads, green lands, and water areas, into distinct modules. Furthermore, we construct two datasets, OSM and GoogleEarth, containing a vast amount of real-world city imagery to enhance the realism of the generated 3D cities both in their layouts and appearances. Through extensive experiments, CityDreamer has proven its superiority over state-of-the-art methods in generating a wide range of lifelike 3D cities.
Infinigen (Raistrick et al., CVPR 2023) a procedural generator of high-quality 3D data. No external assets, it's free and open source. By @PrincetonVL#GameDev
Project: https://t.co/qdG3lRSnJ7
Code: https://t.co/hf6XAlTVgXβ¦
Paper: https://t.co/8J3PzXcFZM
@sterlingcrispin no one is worried about the privacy implications of continuous 3D scanning of your most private environments (in addition to your body/eyes/feelings)?? or do we only freak about having the right webcam cover color to go with our macbook?
@nessuno2001 fantastic thread, hadn't noticed it in the film, but def reminds of how a child glances at their parents/audience whenever they're looking for approval/encouragement when they're doing something. "am I doing this right? are you looking?" saw it yesterday at my kid's school play!
That's it for this thread, but you can also do #Toys, #Jewelry, #Prop & #Set#Design, #NFTs, and #Furniture for example. If you found this thread intriguing, please like and retweet the first tweet now, and check out https://t.co/TnAK6znYoB!
Today we're launching https://t.co/mwQwUDeYsl - the lightweight 3D Ai studio for quickly generating design ideas (and mood boards) from your 3D models from anywhere, including your mobile. What kind of design? Everything #3d, here's a breakdown in the thread: