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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 1854 papers

TitleStatusHype
Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head SynthesisCode11
Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from BackboneCode6
Versatile Diffusion: Text, Images and Variations All in One Diffusion ModelCode6
ControlVAE: Tuning, Analytical Properties, and Performance AnalysisCode4
UniK3D: Universal Camera Monocular 3D EstimationCode4
DEADiff: An Efficient Stylization Diffusion Model with Disentangled RepresentationsCode3
Sigmoid Loss for Language Image Pre-TrainingCode3
UCF: Uncovering Common Features for Generalizable Deepfake DetectionCode3
Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional RepresentationCode2
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text AlignmentCode2
Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty LearningCode2
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D GenerationCode2
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face AnimationCode2
eVAE: Evolutionary Variational AutoencoderCode2
A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild ImagesCode2
ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape DisentanglementCode2
Compositional Transformers for Scene GenerationCode2
BlendFace: Re-designing Identity Encoders for Face-SwappingCode2
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image SynthesisCode2
Adversarial Latent AutoencodersCode2
Compositional Transformers for Scene GenerationCode2
CausalVAE: Structured Causal Disentanglement in Variational AutoencoderCode2
DLF: Disentangled-Language-Focused Multimodal Sentiment AnalysisCode2
A Style-Based Generator Architecture for Generative Adversarial NetworksCode2
Show:102550
← PrevPage 1 of 75Next →

No leaderboard results yet.