DTTD-Mobile

Dataset Information
Modalities
Images, Videos, 3D
Introduced
2023
License
MIT
Homepage
Official Website
Contents

Overview

Are current 3D object tracking methods truely robust enough for low-fidelity depth sensors like the iPhone LiDAR?
We introduce DTTD-Mobile (fully compatible w/ YCB toolbox), a new benchmark built on real-world data captured from mobile devices; 18 objects observed in 100 videos with 47,668 sampled frames and 114,143 object annotations. We evaluate several popular methods—including BundleSDF, ES6D, MegaPose, and DenseFusion—and highlight their limitations in this challenging setting.

Keywords: ObjectPoseEstimation, MobileAI, EdgeAI, ARVR, CVPR

Variants: DTTD-Mobile

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
6D Pose Estimation 6D OBJECT POSE TRACKING IN INTERNET VIDEOS FOR ROBOTIC MANIPULATION 6D Object Pose Tracking in … 2025-03-13
6D Pose Estimation FoundPose FoundPose: Unseen Object Pose Estimation … 2023-11-30
6D Pose Estimation GigaPose GigaPose: Fast and Robust Novel … 2023-11-23
6D Pose Estimation DTTDNet Robust 6DoF Pose Estimation Against … 2023-09-24
3D Object Detection DTTDNet Robust 6DoF Pose Estimation Against … 2023-09-24
3D Object Detection BundleSDF BundleSDF: Neural 6-DoF Tracking and … 2023-03-24
6D Pose Estimation BundleSDF BundleSDF: Neural 6-DoF Tracking and … 2023-03-24
6D Pose Estimation MegaPose-RGBD (Coarse) MegaPose: 6D Pose Estimation of … 2022-12-13
3D Object Detection MegaPose-RGBD MegaPose: 6D Pose Estimation of … 2022-12-13
6D Pose Estimation MegaPose-RGBD (refined) MegaPose: 6D Pose Estimation of … 2022-12-13
6D Pose Estimation ES6D ES6D: A Computation Efficient and … 2022-04-03
3D Object Detection ES6D ES6D: A Computation Efficient and … 2022-04-03
3D Object Detection DenseFusion DenseFusion: 6D Object Pose Estimation … 2019-01-15

Research Papers

Recent papers with results on this dataset:

External Links: