Guess what moves: unsupervised video and image segmentation by anticipating motion
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not move. In this work, we propose an approach that combines the st...
Main Authors: | Choudhury, S, Karazija, L, Laina, I, Vedaldi, A, Rupprecht, C |
---|---|
Format: | Conference item |
Language: | English |
Published: |
British Machine Vision Association
2022
|
Similar Items
-
Unsupervised multi-object segmentation by predicting probable motion patterns
by: Karazija, L, et al.
Published: (2022) -
Diffusion models for open-vocabulary segmentation
by: Karazija, L, et al.
Published: (2024) -
Finding an unsupervised image segmenter in each of your deep generative models
by: Melas-Kyriazi, L, et al.
Published: (2021) -
Unsupervised part discovery from contrastive reconstruction
by: Choudhury, S, et al.
Published: (2021) -
Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization
by: Melas-Kyriazi, L, et al.
Published: (2022)