ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
원문 초록
We introduce the task of 3D object localization in RGB-D scans using natural language descriptions. As input, we assume a point cloud of a scanned 3D scene along with a free-form description of a specified target object. To address this task, we propose ScanRefer, learning a fused descriptor from 3D object proposals and encoded sentence embeddings. This fused descriptor correlates language expressions with geometric features, enabling regression of the 3D bounding box of a target object. We also introduce the ScanRefer dataset, containing 51,583 descriptions of 11,046 objects from 800 ScanNet scenes. ScanRefer is the first large-scale effort to perform object localization via natural language expression directly in 3D.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Single-Document Summarization Using Sentence Embeddings and K-Means Clustering
From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval
Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
Mechanistic Decomposition of Sentence Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.