Thomas Funkhouser

papers

4,301

total citations

papers (24)

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

CVPR 2023arXiv

418

citations

Urban Radiance Fields

CVPR 2022arXiv

323

citations

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

CVPR 2022arXiv

310

citations

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

CVPR 2022arXiv

232

citations

Virtual Multi-view Fusion for 3D Semantic Segmentation

ECCV 2020arXiv

180

citations

Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

CVPR 2021arXiv

172

citations

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

ECCV 2020arXiv

citations

Contrastive Multimodal Fusion With TupleInfoNCE

ICCV 2021arXiv

citations

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision

CVPR 2023arXiv

citations

Multiresolution Deep Implicit Functions for 3D Shape Representation

ICCV 2021arXiv

citations

Adversarial Texture Optimization From RGB-D Scans

CVPR 2020arXiv

citations

Local Deep Implicit Functions for 3D Shape

CVPR 2020arXiv

citations

DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes

CVPR 2020arXiv

citations

Forecasting Characteristic 3D Poses of Human Actions

CVPR 2022arXiv

citations

Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

CVPR 2021arXiv

citations

Revisiting 3D Object Detection From an Egocentric Perspective

NEURIPS 2021arXiv

citations

Polynomial Neural Fields for Subband Decomposition and Manipulation

NEURIPS 2022arXiv

citations

SplatTalk: 3D VQA with Gaussian Splatting

ICCV 2025arXiv

citations

Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting

ICCV 2023arXiv

citations

FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations

CVPR 2024arXiv

citations

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

ICCV 2025arXiv

citations

Thomas Funkhouser

papers (24)

IBRNet: Learning Multi-View Image-Based Rendering

Local Implicit Grid Representations for 3D Scenes

OpenScene: 3D Scene Understanding With Open Vocabularies

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Urban Radiance Fields

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Virtual Multi-view Fusion for 3D Semantic Segmentation

Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Contrastive Multimodal Fusion With TupleInfoNCE

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision

Multiresolution Deep Implicit Functions for 3D Shape Representation

Adversarial Texture Optimization From RGB-D Scans

Local Deep Implicit Functions for 3D Shape

DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes

Forecasting Characteristic 3D Poses of Human Actions

Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

Revisiting 3D Object Detection From an Egocentric Perspective

Polynomial Neural Fields for Subband Decomposition and Manipulation

SplatTalk: 3D VQA with Gaussian Splatting

Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting

FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

papers (24)

IBRNet: Learning Multi-View Image-Based Rendering

Local Implicit Grid Representations for 3D Scenes

OpenScene: 3D Scene Understanding With Open Vocabularies

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Urban Radiance Fields

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Virtual Multi-view Fusion for 3D Semantic Segmentation

Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Contrastive Multimodal Fusion With TupleInfoNCE

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision

Multiresolution Deep Implicit Functions for 3D Shape Representation

Adversarial Texture Optimization From RGB-D Scans

Local Deep Implicit Functions for 3D Shape

DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes

Forecasting Characteristic 3D Poses of Human Actions

Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments

Revisiting 3D Object Detection From an Egocentric Perspective

Polynomial Neural Fields for Subband Decomposition and Manipulation

SplatTalk: 3D VQA with Gaussian Splatting

Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting

FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images