Search Results for author:
Found 3 papers, 2 papers with code
NViST: In the Wild New View Synthesis from a Single Image with Transformers
We propose NViST, a transformer-based model for efficient and generalizable novel-view synthesis from a single image for real-world scenes.
CodeNeRF: Disentangled Neural Radiance Fields for Object Categories
At test time, given a single unposed image of an unseen object, CodeNeRF jointly estimates camera viewpoint, and shape and appearance codes via optimization.
Sampling Using Neural Networks for colorizing the grayscale images
CWGAN-GP tends to generate more diverse images than other models using reconstruction loss.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
