OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects

TL;DR

OmniNOCS introduces a comprehensive large-scale dataset and a transformer-based model for accurate 3D object shape, pose, and segmentation prediction from 2D images, advancing 3D understanding in diverse scenes.

Contribution

The paper presents OmniNOCS, a significantly larger and more diverse dataset, and NOCSformer, a novel transformer-based model capable of generalizing across many object classes for 3D prediction.

Findings

NOCSformer achieves state-of-the-art results in 3D bounding box prediction.

The dataset enables training models with broad class generalization.

The model provides detailed 3D shape and segmentation information.

Abstract

We propose OmniNOCS, a large-scale monocular dataset with 3D Normalized Object Coordinate Space (NOCS) maps, object masks, and 3D bounding box annotations for indoor and outdoor scenes. OmniNOCS has 20 times more object classes and 200 times more instances than existing NOCS datasets (NOCS-Real275, Wild6D). We use OmniNOCS to train a novel, transformer-based monocular NOCS prediction model (NOCSformer) that can predict accurate NOCS, instance masks and poses from 2D object detections across diverse classes. It is the first NOCS model that can generalize to a broad range of classes when prompted with 2D boxes. We evaluate our model on the task of 3D oriented bounding box prediction, where it achieves comparable results to state-of-the-art 3D detection methods such as Cube R-CNN. Unlike other 3D detection methods, our model also provides detailed and accurate 3D object shape and segmentation. We propose a novel benchmark for the task of NOCS prediction based on OmniNOCS, which we hope will serve as a useful baseline for future work in this area. Our dataset and code will be at the project website: https://omninocs.github.io.