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 1–50 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
UniK3D: Universal Camera Monocular 3D EstimationCode4
ControlVAE: Tuning, Analytical Properties, and Performance AnalysisCode4
DEADiff: An Efficient Stylization Diffusion Model with Disentangled RepresentationsCode3
Sigmoid Loss for Language Image Pre-TrainingCode3
UCF: Uncovering Common Features for Generalizable Deepfake DetectionCode3
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text EncoderCode2
Preserving Fairness Generalization in Deepfake DetectionCode2
Realistic and Efficient Face Swapping: A Unified Approach with Diffusion ModelsCode2
SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and EnhancementCode2
Challenging Common Assumptions in the Unsupervised Learning of Disentangled RepresentationsCode2
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance ControlCode2
StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style AdapterCode2
Learning an Animatable Detailed 3D Face Model from In-The-Wild ImagesCode2
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
Generative Time Series Forecasting with Diffusion, Denoise, and DisentanglementCode2
Memory MosaicsCode2
Generative Adversarial TransformersCode2
BlendFace: Re-designing Identity Encoders for Face-SwappingCode2
Interpreting the Latent Space of GANs for Semantic Face EditingCode2
ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape DisentanglementCode2
Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival PredictionCode2
Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty LearningCode2
A Style-Based Generator Architecture for Generative Adversarial NetworksCode2
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text AlignmentCode2
Stylized Neural PaintingCode2
Compositional Transformers for Scene GenerationCode2
Third Time's the Charm? Image and Video Editing with StyleGAN3Code2
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D GenerationCode2
DiffArtist: Towards Structure and Appearance Controllable Image StylizationCode2
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image SynthesisCode2
Compositional Transformers for Scene GenerationCode2
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face AnimationCode2
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical PerspectivesCode2
DLF: Disentangled-Language-Focused Multimodal Sentiment AnalysisCode2
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional RepresentationCode2
eVAE: Evolutionary Variational AutoencoderCode2
Fine-Grained Face Swapping via Regional GAN InversionCode2
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized TasksCode2
Adversarial Latent AutoencodersCode2
A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild ImagesCode2
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image GenerationCode2
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling SpeakersCode2
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementCode2
MotionCLIP: Exposing Human Motion Generation to CLIP SpaceCode2
CausalVAE: Structured Causal Disentanglement in Variational AutoencoderCode2
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image GenerationCode2
Show:102550
← PrevPage 1 of 38Next →

No leaderboard results yet.