Add to Favourites
To login click here

The 2023 edition of CVPR, the prestigious annual conference for computer vision and pattern recognition, is taking place from June 19 to 22 in Vancouver, Canada. Google Research is one of the major sponsors, presenting 90 papers on various topics like image recognition, 3D vision, and machine learning. This article looks at three of the top papers presented at the conference, including MobileNeRF, DynIBaR, and DreamBooth. MobileNeRF introduces a new NeRF representation using textured polygons for efficient image synthesis, while DynIBaR presents a new method for generating realistic views from monocular videos of dynamic scenes. DreamBooth introduces a new method for text-to-image synthesis, combining a generative adversarial network (GAN) with a variational autoencoder (VAE).