See It All: Contextualized Late Aggregation for 3D Dense Captioning

TL;DR

This paper introduces SIA, a transformer-based approach for 3D dense captioning that uses late aggregation of context and object queries to improve caption quality and localization accuracy.

Contribution

The paper proposes a novel late aggregation paradigm with separate context and instance queries, enhancing 3D dense captioning performance over prior methods.

Findings

Significant improvement over previous methods on benchmark datasets.

Effective use of separate queries for context and objects.

Enhanced caption quality through a new aggregator.

Abstract

3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transformer encoder-decoder frameworks from object detection to build an end-to-end pipeline without hand-crafted components. However, these approaches struggle with contradicting objectives where a single query attention has to simultaneously view both the tightly localized object regions and contextual environment. To overcome this challenge, we introduce SIA (See-It-All), a transformer pipeline that engages in 3D dense captioning with a novel paradigm called late aggregation. SIA simultaneously decodes two sets of queries-context query and instance query. The instance query focuses on localization and object attribute descriptions, while the context query versatilely captures the region-of-interest of relationships between multiple objects or with the global scene, then aggregated afterwards (i.e., late aggregation) via simple distance-based measures. To further enhance the quality of contextualized caption generation, we design a novel aggregator to generate a fully informed caption based on the surrounding context, the global environment, and object instances. Extensive experiments on two of the most widely-used 3D dense captioning datasets demonstrate that our proposed method achieves a significant improvement over prior methods.