Jia Deng

papers

5,896

total citations

papers (25)

Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

ICCV 2025arXiv

citations

Princeton365: A Diverse Dataset with Accurate Camera Pose

ICCV 2025arXiv

citations

Learning to Generate 3D Training Data Through Hybrid Gradient

CVPR 2020

citations

Jia Deng

papers (25)

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Deep Patch Visual Odometry

Advancing LLM Reasoning Generalists with Preference Trees

RAFT-3D: Scene Flow Using Rigid-Motion Embeddings

How Useful Is Self-Supervised Pretraining for Visual Tasks?

Infinite Photorealistic Worlds Using Procedural Generation

Non-deep Networks

Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation

Siamese Masked Autoencoders

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Multiview Stereo with Cascaded Epipolar RAFT

Tangent Space Backpropagation for 3D Transformation Groups

Learning to Prove Theorems by Learning to Generate Theorems

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Strongly Incremental Constituency Parsing with Graph Neural Networks

OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

Convolutional Networks with Oriented 1D Kernels

Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization

Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

Princeton365: A Diverse Dataset with Accurate Camera Pose

Learning to Generate 3D Training Data Through Hybrid Gradient

papers (25)

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Deep Patch Visual Odometry

Advancing LLM Reasoning Generalists with Preference Trees

RAFT-3D: Scene Flow Using Rigid-Motion Embeddings

How Useful Is Self-Supervised Pretraining for Visual Tasks?

Infinite Photorealistic Worlds Using Procedural Generation

Non-deep Networks

Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation

Siamese Masked Autoencoders

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Multiview Stereo with Cascaded Epipolar RAFT

Tangent Space Backpropagation for 3D Transformation Groups

Learning to Prove Theorems by Learning to Generate Theorems

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Strongly Incremental Constituency Parsing with Graph Neural Networks

OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

Convolutional Networks with Oriented 1D Kernels

Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization

Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

Princeton365: A Diverse Dataset with Accurate Camera Pose

Learning to Generate 3D Training Data Through Hybrid Gradient