Results 251 to 260 of about 16,932 (278)

Scene-Aware Foveated Neural Radiance Fields

IEEE Transactions on Visualization and Computer Graphics
Foveated rendering provides an idea for improving the image synthesis performance of neural radiance fields (NeRF) methods. In this paper, we propose a scene-aware foveated neural radiance fields method to synthesize high-quality foveated images in complex VR scenes at high frame rates. Firstly, we construct a multi-ellipsoidal neural representation to
Xuehuai, Lili Wang
exaly   +3 more sources

Instant Neural Radiance Fields

Special Interest Group on Computer Graphics and Interactive Techniques Conference Real-Time Live!, 2022
Thomas Müller, Alex Evans, Christoph Schied, Marco Foco, András Bódis-Szomorú, Isaac Deutsch, Michael Shelley, Alexander Keller   +7 more
openaire   +1 more source

Multimodal Neural Radiance Field

2023 IEEE International Conference on Robotics and Automation (ICRA), 2023
Haidong Zhu, Yuyin Sun, Chi Liu, Lu Xia, Jiajia Luo, Nan Qiao, Ram Nevatia, Cheng–Hao Kuo   +7 more
openaire   +1 more source

Multi-Space Neural Radiance Fields

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Ze-Xin Yin, Jiaxiong Qiu, Ming-Ming Cheng, Bo Ren   +3 more
openaire   +1 more source

A Survey on Neural Radiance Fields

ACM Computing Surveys
View synthesis is a fundamental task in computer vision, known for its significantly higher complexity compared to conventional vision problems. The introduction of Neural Radiance Fields (NeRF) marked a major breakthrough in this field, substantially improving previous methods and pushing view synthesis to unprecedented levels.
Yun Liao, Yide Di, Hao Zhou, Kaijun Zhu, Mingyu Lu, Qing Duan, Junhui Liu   +6 more
openaire   +1 more source

3D Gaussian Splatting for Real-Time Radiance Field Rendering

ACM Transactions on Graphics, 2023
Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuehler   +2 more
exaly  

NEURAL RADIANCE FIELDS IN COMPUTER VISION

Neural radiance fields (NeRFs) are like magic paintbrushes for 3D scenes. They're a cutting-edge technique that uses the power of deep learning to transform a few 2D photos into a complete, interactive 3D model. Imagine taking just a handful of pictures of a statue and then being able to walk around it virtually, seeing it from any angle with stunning ...
Dr. Sharda Chhabria, Tanmay Kapure
openaire   +1 more source

HyperNeRF

ACM Transactions on Graphics, 2021
Peter Hedman
exaly  

Neural Radiance Fields for Landscape Architecture

2023
Schob, Maximilian, Rekittke, Jörg
openaire   +1 more source