Kevis-Kokitsi Maninis

New paper 📢📢 TL;DR: We introduce OmniNOCS: a multi-domain NOCS dataset with 90+ object classes. Our model trained on OmniNOCS can predict 6DoF object pose and partial shape from their 2D detections, even generalizing to in-the-wild images! Background & details in 🧵 below

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

Google announces Probing the 3D Awareness of Visual Foundation Models Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their