Van Nguyen NGUYEN

Pose Estimation of Novel Rigid Objects

BOP Challenge 2024 on Model-free, Model-based Detection, and Pose Estimation of Unseen Rigid Objects

We introduce a new model-free variant of all tasks, define a new 6D object detection task, and introduce three new publicly available datasets

BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects

The report of BOP challenge 2023 on state-of-the-art methods for seen and unseen object pose estimation.

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

A "hybrid" template-patch correspondence approach that is fast, robust, and more accurate to estimate 6D pose of novel objects in RGB images. GigaPose predicts 6D object pose from a single 2D-to-2D correspondence.

NOPE: Novel Object Pose Estimation from a Single Image

A method that can estimate relative pose of unseen objects given only a single reference image. Our method also predicts 3D pose distribution which can be used to address pose ambiguities due to symmetries.

OpenStreetView-5M: The Many Roads to Global Visual Geolocation

A new benchmark for visual geolocation (~Geoguessr).

CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

A method that can segment novel objects for a given RGB image from only their CAD models. Based on Segmenting Anything, DINOv2, CNOS is a strong baseline for Task 5 and 6 in the BOP challenge 2023.

PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6DoF Tracking

A method for tracking the 6D motion of objects in RGB video sequences when neither training images nor even the 3D geometry of the objects is available.

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

A method that can recognize objects and estimate their 3D pose in color images even under partial occlusions. Our method requires neither a training phase on these objects nor real images depicting them, only their CAD models.