SOTAVerified

Disentanglement

This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)

Papers

Showing 3140 of 1854 papers

TitleStatusHype
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
Generative Time Series Forecasting with Diffusion, Denoise, and DisentanglementCode2
eVAE: Evolutionary Variational AutoencoderCode2
Fine-Grained Face Swapping via Regional GAN InversionCode2
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical PerspectivesCode2
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling SpeakersCode2
MotionCLIP: Exposing Human Motion Generation to CLIP SpaceCode2
Third Time's the Charm? Image and Video Editing with StyleGAN3Code2
Compositional Transformers for Scene GenerationCode2
Show:102550
← PrevPage 4 of 186Next →

No leaderboard results yet.