Unifying 3D Vision-Language Understanding via Promptable Queries

TL;DR

This paper introduces PQ3D, a unified 3D vision-language model that leverages promptable queries to handle diverse 3D scene representations and tasks, achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper proposes a novel unified framework with promptable queries, unifying various 3D scene representations and enabling multi-task learning for 3D vision-language understanding.

Findings

Achieves new state-of-the-art on multiple 3D-VL benchmarks.

Supports flexible inference with different 3D representations.

Demonstrates significant performance improvements over existing methods.

Abstract

A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the independent application of representation and insufficient exploration of 3D multi-task training. In this paper, we introduce PQ3D, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmentation to high-level reasoning and planning. This is achieved through three key innovations: (1) unifying various 3D scene representations (i.e., voxels, point clouds, multi-view images) into a shared 3D coordinate space by segment-level grouping, (2) an attention-based query decoder for task-specific information retrieval guided by prompts, and (3) universal output heads for different tasks to support multi-task training. Tested across ten diverse 3D-VL datasets, PQ3D demonstrates impressive performance on these tasks, setting new records on most benchmarks. Particularly, PQ3D improves the state-of-the-art on ScanNet200 by 4.9% (AP25), ScanRefer by 5.4% (acc@0.5), Multi3DRefer by 11.7% (F1@0.5), and Scan2Cap by 13.4% (CIDEr@0.5). Moreover, PQ3D supports flexible inference with individual or combined forms of available 3D representations, e.g., solely voxel input.