We propose a novel-view augmentation (NOVA) strategy to train NeRFs for
...
We present SSOD, the first end-to-end analysis-by synthesis framework wi...
Neural rendering techniques promise efficient photo-realistic image synt...
Training deep neural networks to estimate the viewpoint of objects requi...
The task of generating natural images from 3D scenes has been a long sta...
We address the task of estimating the 6D pose of known rigid objects, fr...
The success of deep learning in computer vision is based on availability...
For state-of-the-art semantic segmentation task, training convolutional
...