LiDAR-based 3D detection methods currently use bird's-eye view (BEV) or range

We further introduce a multi-scale diversity penalty that operates in the feature space of our discriminators.

Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models. Specifically, our method employs semantic masks from foundation models to guide the masking and reconstruction process for the masked autoen-coder, enabling more focused attention on foreground representations.

This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly.

For what purpose was the dataset created? We created this CityRefer dataset to facilitate research toward city-scale 3D visual grounding. Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., Who funded the creation of the dataset? What do the instances that comprise the dataset represent? CityRefer contains descriptions for 3D visual grounding on large-scale point cloud data.

In this paper, we introduce the CityRefer dataset for city-level 3D visual grounding.

Differently, our unsupervised multi-body task requires the model's ability to handle part-level local equivariance, Figure 1: Structure of our feature extractor based on EPN. "EPNConv" is the SE(3)-equivariant convolution proposed in the vanilla EPN network. Part-level SE(3)-equivariance is desirable for motion analysis, especially rotation estimation. Song and Y ang utilized the methodology proposed by Choy et al . All other objects were considered part of the background.

A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes.