Shalini De Mello

papers

3,754

total citations

papers (26)

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

CVPR 2024arXiv

citations

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

CVPR 2025arXiv

citations

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

NEURIPS 2025arXiv

citations

Self-Supervised Object Detection via Generative Image Synthesis

ICCV 2021arXiv

citations

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

CVPR 2025arXiv

citations

BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

CVPR 2025

citations

Generalizable One-shot 3D Neural Head Avatar

NEURIPS 2023

citations

Shalini De Mello

papers (26)

Efficient Geometry-Aware 3D Generative Adversarial Networks

GroupViT: Semantic Segmentation Emerges From Text Supervision

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

FreeSOLO: Learning To Segment Objects Without Annotations

Affordance Diffusion: Synthesizing Hand-Object Interactions

A Unified Approach for Text- and Image-guided 4D Scene Generation

RegionGPT: Towards Region Understanding Vision Language Model

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Weakly-Supervised Physically Unconstrained Gaze Estimation

Self-Learning Transformations for Improving Gaze and Head Redirection

Self-Supervised Viewpoint Learning From Image Collections

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

Learning to Track Instances without Video Annotations

CoordGAN: Self-Supervised Dense Correspondences Emerge From GANs

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

Self-Supervised Object Detection via Generative Image Synthesis

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

Generalizable One-shot 3D Neural Head Avatar

papers (26)

Efficient Geometry-Aware 3D Generative Adversarial Networks

GroupViT: Semantic Segmentation Emerges From Text Supervision

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

FreeSOLO: Learning To Segment Objects Without Annotations

Affordance Diffusion: Synthesizing Hand-Object Interactions

A Unified Approach for Text- and Image-guided 4D Scene Generation

RegionGPT: Towards Region Understanding Vision Language Model

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Weakly-Supervised Physically Unconstrained Gaze Estimation

Self-Learning Transformations for Improving Gaze and Head Redirection

Self-Supervised Viewpoint Learning From Image Collections

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

Learning to Track Instances without Video Annotations

CoordGAN: Self-Supervised Dense Correspondences Emerge From GANs

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

Self-Supervised Object Detection via Generative Image Synthesis

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

Generalizable One-shot 3D Neural Head Avatar