RebuilderAI_Blog

Maybe you are all familiar with the keyword "Virtual Space". Virtual space is very similar to the real world, and it has no time and space constraints. Many companies around the world have already introduced projects utilizing virtual space. Especially, both Samsung and LG electronics provide a 'virtual showroom' service that allows to combine home appliances in a virtual space. You can feel the..

by Sanghyeon AN (AI research engineer / R&D) Today we are sharing Semantic Segmentation for Point Clouds | RebuilderAI Semantic Segmentation for Point Clouds | RebuilderAI Semantic segmentation survey RebuilderAI.github.io More available information is here: Home | RebuilderAI Home | RebuilderAI 리빌더에이아이 테크 블로그 RebuilderAI.github.io Table of Contents 1. Datasets 2. Evaluation Metrics 3. Methods S..

Hello. This is RebuilderAI. Today we will talk about 'NFT', which is often mentioned nowadays. Maybe you all have heard the word NFT, but there are few people who can explain exactly what NFT is. Therefore, let's check out what is NFT, what is its character and advantage, and how does it related to the 3D model in today's post. What is NFT? NFT (aka. non-fungible token) is a virtual token that u..

Due to COVID-19, metaverse (A virtual world) is growing rapidly so various institutions and companies are striving to develop content using 3D. A case in point, "Kakao Friends" gained popularity by uploading a video of expressing in 3D with popular characters RYAN&CHOONSIK and copying the choreography of famous K-pop idols. Maybe you’ve seen this video at least once. The cover video of SM girl g..

by Gwan hyeong Koo, Sehyeon Kim (Research Intern) 일반 인공지능을 향하여 | RebuilderAI Brief introduction to multi-modal learning AI models RebuilderAI.github.io More available information is here: Home | RebuilderAI Home | RebuilderAI 리빌더에이아이 테크 블로그 RebuilderAI.github.io 1. Multimodal learning 2. CLIP, a new model of object recognition 3. Flamingo: Interactive AI technology that maximizes user interactio..

Check out the guide: how to take videos and use VRIN. 1. Click the 'camera' button and choose 'Take video' or 'Choose from library'. By the way, the video from library will be uploaded more clearly. *You have to check those lists before uploading the video. Please make sure not to take the video on the single-color floor and change the video mode to 60fps. If you need more detail, then you can t..

by Geunho Jung (AI researcher / R&D) Our RebuilderAI R&D team is introducing COLMAP this week. Structure-from-Motion: COLMAP | RebuilderAI Structure-from-Motion: COLMAP | RebuilderAI How to process multiple images RebuilderAI.github.io More available information is here: Home | RebuilderAI Home | RebuilderAI 리빌더에이아이 테크 블로그 RebuilderAI.github.io Before introducing the technology, let me tell the ..

by Sanghyeon An (AI research engineer / R&D) Today we are sharing U^2-Net:Going Deeper with Nested U-Structure for Salient Object Detection | RebuilderAI U^2-Net:Going Deeper with Nested U-Structure for Salient Object Detection | RebuilderAI Salient Object Detection model in PR 2020 RebuilderAI.github.io More available information is here: Home | RebuilderAI Home | RebuilderAI 리빌더에이아이 테크 블로그 Reb..