Conversation agents fueled by Large Language Models (LLMs) are providing a new way to
interact with visual data. While there have been initial attempts for image-based …

Emerging neural radiance fields (NeRF) are a promising scene representation for computer
graphics, enabling high-quality 3D reconstruction and novel view synthesis from image …

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

We present ScanNet++, a large-scale dataset that couples together capture of high-quality
and commodity-level geometry and color of indoor scenes. Each scene is captured with a …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

This paper is not motivated to seek innovation within the attention mechanism. Instead it
focuses on overcoming the existing trade-offs between accuracy and efficiency within the …

We introduce OpenShape, a method for learning multi-modal joint representations of text,
image, and point clouds. We adopt the commonly used multi-modal contrastive learning …

The rapid advancement of deep learning models is often attributed to their ability to leverage
massive training data. In contrast such privilege has not yet fully benefited 3D deep learning …

Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

We introduce the task of localizing a flexible number of objects in real-world 3D scenes
using natural language descriptions. Existing 3D visual grounding tasks focus on localizing …