Justin Johnson

papers

3,209

total citations

papers (26)

CASTing Your Model: Learning To Localize Improves Self-Supervised Representations

CVPR 2021arXiv

citations

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

CVPR 2024arXiv

citations

StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

CVPR 2022arXiv

citations

UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

CVPR 2021arXiv

citations

FWD: Real-Time Novel View Synthesis With Forward Warping and Depth

CVPR 2022arXiv

citations

Bootstrap Your Own Correspondences

ICCV 2021arXiv

citations

Learning Visual Representations via Language-Guided Sampling

CVPR 2023arXiv

citations

View Selection for 3D Captioning via Diffusion Ranking

ECCV 2024arXiv

citations

Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization

ICCV 2025arXiv

citations

Learning 3D Object Shape and Layout Without 3D Supervision

CVPR 2022arXiv

citations

Benchmarking Object Detectors with COCO: A New Path Forward

ECCV 2024arXiv

citations

RGB No More: Minimally-Decoded JPEG Vision Transformers

CVPR 2023arXiv

citations

FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation

CVPR 2024arXiv

citations

PointInfinity: Resolution-Invariant Point Diffusion Models

CVPR 2024arXiv

citations

Visual Test-time Scaling for GUI Agent Grounding

ICCV 2025arXiv

citations

Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data

CVPR 2023arXiv

citations

Directed Ray Distance Functions for 3D Scene Reconstruction

ECCV 2022

citations

Justin Johnson

papers (26)

HexPlane: A Fast Representation for Dynamic Scenes

SynSin: End-to-End View Synthesis From a Single Image

VirTex: Learning Visual Representations From Textual Annotations

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models

Scalable 3D Captioning with Pretrained Models

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

Probing the 3D Awareness of Visual Foundation Models

PixelSynth: Generating a 3D-Consistent Experience From a Single Image

Multiview Compressive Coding for 3D Reconstruction

CASTing Your Model: Learning To Localize Improves Self-Supervised Representations

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

FWD: Real-Time Novel View Synthesis With Forward Warping and Depth

Bootstrap Your Own Correspondences

Learning Visual Representations via Language-Guided Sampling

View Selection for 3D Captioning via Diffusion Ranking

Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization

Learning 3D Object Shape and Layout Without 3D Supervision

Benchmarking Object Detectors with COCO: A New Path Forward

RGB No More: Minimally-Decoded JPEG Vision Transformers

FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation

PointInfinity: Resolution-Invariant Point Diffusion Models

Visual Test-time Scaling for GUI Agent Grounding

Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data

Directed Ray Distance Functions for 3D Scene Reconstruction

papers (26)

HexPlane: A Fast Representation for Dynamic Scenes

SynSin: End-to-End View Synthesis From a Single Image

VirTex: Learning Visual Representations From Textual Annotations

Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models

Scalable 3D Captioning with Pretrained Models

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

Probing the 3D Awareness of Visual Foundation Models

PixelSynth: Generating a 3D-Consistent Experience From a Single Image

Multiview Compressive Coding for 3D Reconstruction

CASTing Your Model: Learning To Localize Improves Self-Supervised Representations

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

FWD: Real-Time Novel View Synthesis With Forward Warping and Depth

Bootstrap Your Own Correspondences

Learning Visual Representations via Language-Guided Sampling

View Selection for 3D Captioning via Diffusion Ranking

Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization

Learning 3D Object Shape and Layout Without 3D Supervision

Benchmarking Object Detectors with COCO: A New Path Forward

RGB No More: Minimally-Decoded JPEG Vision Transformers

FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation

PointInfinity: Resolution-Invariant Point Diffusion Models

Visual Test-time Scaling for GUI Agent Grounding

Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data

Directed Ray Distance Functions for 3D Scene Reconstruction