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 111120 of 1854 papers

TitleStatusHype
Decoupled Textual Embeddings for Customized Image GenerationCode1
Point Cloud Part Editing: Segmentation, Generation, Assembly, and SelectionCode1
Beyond Prototypes: Semantic Anchor Regularization for Better Representation LearningCode1
Ins-HOI: Instance Aware Human-Object Interactions RecoveryCode1
AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style TransferCode1
GIR: 3D Gaussian Inverse Rendering for Relightable Scene FactorizationCode1
MotionCrafter: One-Shot Motion Customization of Diffusion ModelsCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
Language-Informed Visual Concept LearningCode1
Dancing with Still Images: Video Distillation via Static-Dynamic DisentanglementCode1
Show:102550
← PrevPage 12 of 186Next →

No leaderboard results yet.