English

Explore and Tell: Embodied Visual Captioning in 3D Environments

Computer Vision and Pattern Recognition 2023-08-22 v1

Abstract

While current visual captioning models have achieved impressive performance, they often assume that the image is well-captured and provides a complete view of the scene. In real-world scenarios, however, a single image may not offer a good viewpoint, hindering fine-grained scene understanding. To overcome this limitation, we propose a novel task called Embodied Captioning, which equips visual captioning models with navigation capabilities, enabling them to actively explore the scene and reduce visual ambiguity from suboptimal viewpoints. Specifically, starting at a random viewpoint, an agent must navigate the environment to gather information from different viewpoints and generate a comprehensive paragraph describing all objects in the scene. To support this task, we build the ET-Cap dataset with Kubric simulator, consisting of 10K 3D scenes with cluttered objects and three annotated paragraphs per scene. We propose a Cascade Embodied Captioning model (CaBOT), which comprises of a navigator and a captioner, to tackle this task. The navigator predicts which actions to take in the environment, while the captioner generates a paragraph description based on the whole navigation trajectory. Extensive experiments demonstrate that our model outperforms other carefully designed baselines. Our dataset, codes and models are available at https://aim3-ruc.github.io/ExploreAndTell.

Keywords

Cite

@article{arxiv.2308.10447,
  title  = {Explore and Tell: Embodied Visual Captioning in 3D Environments},
  author = {Anwen Hu and Shizhe Chen and Liang Zhang and Qin Jin},
  journal= {arXiv preprint arXiv:2308.10447},
  year   = {2023}
}

Comments

12 pages; 10 figures; ICCV 2023

R2 v1 2026-06-28T12:00:02.397Z