Pith. sign in

Title resolution pending

First demonstration of totally unsupervised GAN based inpainting on videos (in context of error concealment) with speedup upto 80× by leveraging temporal redundancy

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.CV 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Faster Unsupervised Semantic Inpainting: A GAN Based Approach

cs.CV · 2019-08-14 · conditional · novelty 5.0

A nearest-neighbor latent initialization plus temporal reuse of the latent code cuts unsupervised GAN inpainting cost by about 5x on images and 80x on coherent video while roughly matching or slightly improving quality.

citing papers explorer

Showing 1 of 1 citing paper.

  • Faster Unsupervised Semantic Inpainting: A GAN Based Approach cs.CV · 2019-08-14 · conditional · none · ref 3

    A nearest-neighbor latent initialization plus temporal reuse of the latent code cuts unsupervised GAN inpainting cost by about 5x on images and 80x on coherent video while roughly matching or slightly improving quality.