Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases
원문 초록
Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description. However, existing methods only consider the dependency between the entire sentence and the target object, ignoring fine-grained relationships between contexts and non-target ones. In this paper, we extend 3DVG to a more fine-grained and interpretable task, called 3D Phrase Aware Grounding (3DPAG). The 3DPAG task aims to localize the target objects in a 3D scene by explicitly identifying all phrase-related objects and then conducting the reasoning according to contextual phrases. To tackle this problem, we manually labeled about 227K phrase-level annotations using a self-developed platform, from 88K sentences of widely used 3DVG datasets, i.e., Nr3D, Sr3D and ScanRefer. By tapping on our datasets, we can extend previous 3DVG methods to the fine-grained phrase-aware scenario. It is achieved through the proposed novel phrase-object alignment optimization and phrase-specific pre-training, boosting conventional 3DVG performance as well. Extensive results confirm significant improvements, i.e., previous state-of-the-art method achieves 3.9%, 3.5% and 4.6% overall accuracy gains on Nr3D, Sr3D and ScanRefer respectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
Unified Representation Space for 3D Visual Grounding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.