Narendra Ahuja

papers

150

total citations

papers (11)

Visual Scene Graphs for Audio Source Separation

ICCV 2021arXiv

citations

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

ICCV 2021arXiv

citations

A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction

ICCV 2021arXiv

citations

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation including the Unseen

AAAI 2024arXiv

citations

Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation

NEURIPS 2022arXiv

citations

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

ICML 2024arXiv

citations

Learning Implicit Representation for Reconstructing Articulated Objects

ICLR 2024arXiv

citations

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

ICCV 2025arXiv

citations

Narendra Ahuja

papers (11)

Visual Scene Graphs for Audio Source Separation

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation including the Unseen

Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

Learning Implicit Representation for Reconstructing Articulated Objects

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

Potential Field Based Deep Metric Learning

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

papers (11)

Visual Scene Graphs for Audio Source Separation

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation including the Unseen

Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

Learning Implicit Representation for Reconstructing Articulated Objects

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

Potential Field Based Deep Metric Learning

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes