Jia-Bin Huang Profile picture
Associate Professor @umdcs; Part-time Research Scientist @Meta. I like pixels.

Jul 20, 2021, 5 tweets

Example 1

Trajectory:
• Learning LR-HR -> challenge: large patch space -> learning mixture of models -> learning 1D profile -> high-level feature

Relationship:
• Contrastive concept: External vs. Internal (no learning)

Source: cv-foundation.org/openaccess/con…

Example 2

Trajectory:
• Applications of vision-based methods for assessment.
• Highlight the closest related work.

Relationship:
• Building upon the methodology... BUT, use deep learning.

Source: Deep Paper Gestalt arxiv.org/abs/1812.08775

Example 3

Trajectory:
• Video completion methods and their use for view synthesis.

Relationship:
• Contrastive concept: \emph{screen space} vs. \emph{3D space}.

Source: arxiv.org/abs/2011.12950

Example 4

Trajectory:
• Different conditions in conditional GANs.
• Image-conditioned models.
• GANs for translation, but only unconditionally

Relationship:
• Contrastive concept: Application-specific vs. Application-agnostic

Source: Pix2Pix arxiv.org/abs/1611.07004

Example 5

Trajectory:
• Initial attempts -> supervised learning -> CNN-based methods

Relationship:
• ALSO a learning-based approach, BUT go beyond ...
• Contrastive concept: 3D supervision <-> Multiview supervision

Source: arxiv.org/abs/1807.10264

Share this Scrolly Tale with your friends.

A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.

Keep scrolling