Kostas Daniilidis

papers

2,126

total citations

papers (28)

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

ECCV 2020arXiv

188

citations

Discovering and Achieving Goals via World Models

NEURIPS 2021arXiv

160

citations

GART: Gaussian Articulated Template Models

CVPR 2024arXiv

131

citations

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

CVPR 2025arXiv

124

citations

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

ECCV 2024arXiv

114

citations

Cross-Modal Map Learning for Vision and Language Navigation

CVPR 2022arXiv

102

citations

Spin-Weighted Spherical CNNs

NEURIPS 2020arXiv

citations

CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism

CVPR 2022arXiv

citations

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

ECCV 2024arXiv

citations

3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

ECCV 2020arXiv

citations

Learning Predictive Models from Observation and Interaction

ECCV 2020arXiv

citations

ReFit: Recurrent Fitting Network for 3D Human Recovery

ICCV 2023arXiv

citations

Birds of a Feather: Capturing Avian Shape Models From Images

CVPR 2021arXiv

citations

EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision

CVPR 2023arXiv

citations

PromptHMR: Promptable Human Mesh Recovery

CVPR 2025arXiv

citations

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

NEURIPS 2023arXiv

citations

EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls

ECCV 2022arXiv

citations

EqNIO: Subequivariant Neural Inertial Odometry

ICLR 2025arXiv

citations

Un-EVIMO: Unsupervised Event-based Independent Motion Segmentation

ECCV 2024arXiv

citations

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

ICCV 2025arXiv

citations

DIMO: Diverse 3D Motion Generation for Arbitrary Objects

ICCV 2025arXiv

citations

ETAP: Event-based Tracking of Any Point

CVPR 2025arXiv

citations

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

NEURIPS 2023

citations

Continuous-Time Human Motion Field from Event Cameras

ICCV 2025

citations

NAP: Neural 3D Articulated Object Prior

NEURIPS 2023

citations

Kostas Daniilidis

papers (28)

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

Coherent Reconstruction of Multiple Humans From a Single Image

Probabilistic Modeling for Human Mesh Recovery

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Discovering and Achieving Goals via World Models

GART: Gaussian Articulated Template Models

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

Cross-Modal Map Learning for Vision and Language Navigation

Spin-Weighted Spherical CNNs

CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

Learning Predictive Models from Observation and Interaction

ReFit: Recurrent Fitting Network for 3D Human Recovery

Birds of a Feather: Capturing Avian Shape Models From Images

EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision

PromptHMR: Promptable Human Mesh Recovery

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls

EqNIO: Subequivariant Neural Inertial Odometry

Un-EVIMO: Unsupervised Event-based Independent Motion Segmentation

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

DIMO: Diverse 3D Motion Generation for Arbitrary Objects

ETAP: Event-based Tracking of Any Point

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

Continuous-Time Human Motion Field from Event Cameras

NAP: Neural 3D Articulated Object Prior

papers (28)

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

Coherent Reconstruction of Multiple Humans From a Single Image

Probabilistic Modeling for Human Mesh Recovery

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Discovering and Achieving Goals via World Models

GART: Gaussian Articulated Template Models

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

Cross-Modal Map Learning for Vision and Language Navigation

Spin-Weighted Spherical CNNs

CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

Learning Predictive Models from Observation and Interaction

ReFit: Recurrent Fitting Network for 3D Human Recovery

Birds of a Feather: Capturing Avian Shape Models From Images

EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision

PromptHMR: Promptable Human Mesh Recovery

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls

EqNIO: Subequivariant Neural Inertial Odometry

Un-EVIMO: Unsupervised Event-based Independent Motion Segmentation

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

DIMO: Diverse 3D Motion Generation for Arbitrary Objects

ETAP: Event-based Tracking of Any Point

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

Continuous-Time Human Motion Field from Event Cameras

NAP: Neural 3D Articulated Object Prior