Shape-aware Text-driven Layered Video Editing
"[A] pre-trained text-conditioned diffusion model as guidance for refining shape distortion and completing unseen regions. The experimental results demonstrate that our method can achieve shape-aware consistent video editing and compare favorably with the state-of-the-art."
BoxInstSeg is a toolbox that aims to provide state-of-the-art box-supervised instance segmentation algorithms.
https://github.com/LiWentomng/BoxInstSeg
https://deepai.org/publication/box2mask-box-supervised-instance-segmentation-via-level-set-evolution
[Google] Muse: Text-To-Image Generation via Masked Generative Transformers
"[A] text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens."
Game streaming with NovelAI + GPT-3 — AI VTuber experiment by Yuske Fukuyama
https://www.nicovideo.jp/watch/sm41575169
https://github.com/fkymy
Deep Reconstruction of 3D Smoke Densities from Artist Sketches
"We present a method to compute a 3D smoke density field directly from 2D artist sketches, bridging the gap between early-stage prototyping of smoke keyframes and pre-visualization."
https://www.youtube.com/watch?v=PF7QqNZ28hk
https://cgl.ethz.ch/publications/papers/paperKim22a.php
