2 papers
cs.CV2024
FSViewFusion: Few-Shots View Generation of Novel Objects
Rukhshanda Hussain, Hui Xian Grace Lim, Borchun Chen +2
Novel view synthesis has observed tremendous developments since the arrival of NeRFs. However, Nerf models overfit on a single scene, lacking generalization to out of distribution…
cs.CV2023
Object Recognition as Next Token Prediction
Kaiyu Yue, Bor-Chun Chen, Jonas Geiping +3
We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embed…