Neural Radiance Fields
Representing Scenes as Neural Radiance Fields for View Synthesis
Traditional Neural Radiance Fields (NeRFs) methods depend heavily on accurately pre-computed camera poses, a time-consuming process prone to failure in textureless or repetitive regions, limiting their practicality in dynamic scene reconstruction.
NeRF Algorithms
[논문 리뷰] 3D Gaussian Splatting (SIGGRAPH 2023) : 랜더링 속도/퀄리티 개선
3D Gaussian Splatting for Real-Time Radiance Field Rendering, Bernhard Kerbl, SIGGRAPH 2023 NeRF분야에서 뜨거운 이슈가 된 논문입니다. NeRF에서 해결하고자 하는 Task와 동일하게, 여러 이미지와 촬영 pose 값이 주어지면 다양한 시점에서 3D Scene을 랜더링합니다. 고해상도(1920x1080)에서 랜더링 Quality가 SOTA인 Mip-NeRF360 (2022)보다 뛰어나고, Training 시간에서 SOTA인 InstantNGP (2022)보다도 시간을 단축시키게 됩니다. 이 논문이 뜨거운 이슈가 된 이유는 위 장점들에 추가적으로 획기적으로 빠른 Rendering속도(약 100FPS이상)입니다. 위 그림에서 괄호는 ..
https://xoft.tistory.com/51
가짜연구소 | Nerd's NeRF 스터디 | D-NeRF Paper & Code Review
https://youtube.com/watch?v=y-4vLEo7hns&feature=shares

NeRF: Neural Radiance Fields
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.
https://www.matthewtancik.com/nerf

Apple's new GAUDI AI turns text prompts into 3D scenes
Apple shows its latest AI system GAUDI. It can generate 3D indoor scenes and is the foundation for a new generation of generative AI based on NeRFs. So-called neural rendering brings artificial intelligence to computer graphics: AI researchers at Nvidia, for example, are showing how 3D objects are created from photos, and Google is relying on Neural Radiance Fields (NeRFs) for Immersive View or developing NeRFs for rendering people.
https://mixed-news.com/en/apples-new-gaudi-ai-turns-text-prompts-into-3d-scenes


Seonglae Cho