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 551–600 of 1854 papers

TitleStatusHype
Ins-HOI: Instance Aware Human-Object Interactions RecoveryCode1
A Compact and Semantic Latent Space for Disentangled and Controllable Image EditingCode0
Resetting a fixed broken ELBO—0
Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images—0
AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style TransferCode1
MotionCrafter: One-Shot Motion Customization of Diffusion ModelsCode1
GIR: 3D Gaussian Inverse Rendering for Relightable Scene FactorizationCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment—0
PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns—0
GenDeF: Learning Generative Deformation Field for Video Generation—0
Language-Informed Visual Concept LearningCode1
Bottom-Up Instance Segmentation of Catheters for Chest X-Rays—0
AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing—0
Dancing with Still Images: Video Distillation via Static-Dynamic DisentanglementCode1
Text Attribute Control via Closed-Loop Disentanglement—0
StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style AdapterCode2
Clustering Inductive Biases with Unrolled Networks—0
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
Benchmarking and Enhancing Disentanglement in Concept-Residual Models—0
When StyleGAN Meets Stable Diffusion: a W_+ Adapter for Personalized Image GenerationCode1
Identifiable Feature Learning for Spatial Data with Nonlinear ICA—0
Clean Label Disentangling for Medical Image Segmentation with Noisy LabelsCode0
The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In VisibilityCode1
Rethinking Directional Integration in Neural Radiance Fields—0
MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation—0
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and CaptionsCode1
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation—0
LFSRDiff: Light Field Image Super-Resolution via Diffusion ModelsCode1
DreamCreature: Crafting Photorealistic Virtual Creatures from ImaginationCode1
Parameter Exchange for Robust Dynamic Domain GeneralizationCode1
An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis—0
Supervised structure learning—0
Concept-free Causal Disentanglement with Variational Graph Auto-EncoderCode0
Cross-domain feature disentanglement for interpretable modeling of tumor microenvironment impact on drug response—0
Predicting Scientific Impact Through Diffusion, Conformity, and Contribution DisentanglementCode0
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations—0
Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification—0
Counterfactual Explanation for Regression via Disentanglement in Latent Space—0
PGODE: Towards High-quality System Dynamics Modeling—0
SCADI: Self-supervised Causal Disentanglement in Latent Variable ModelsCode0
Towards a Unified Framework of Contrastive Learning for Disentangled Representations—0
Anonymizing medical case-based explanations through disentanglement—0
Multi-View Causal Representation Learning with Partial ObservabilityCode1
Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational AutoencoderCode1
Learning Disentangled Speech Representations—0
Disentangled Representation Learning with Transmitted Information Bottleneck—0
Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from BackboneCode6
Object-centric architectures enable efficient causal representation learningCode0
FPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic DataCode1
Show:102550
← PrevPage 12 of 38Next →

No leaderboard results yet.