CVJul 14

SaaF: Scene-Specific Ambiguity-Aware 3D Language Fields towards Interactive Real-World Object Retrieval

arXiv:2607.1630913.1h-index: 12
Predicted impact top 24% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For service robots needing interactive object retrieval in real-world scenes, SaaF addresses the bottleneck of ambiguous queries and similar-object confusion, offering a practical improvement over existing 3D language fields.

SaaF improves 3D object retrieval accuracy by 15% over prior methods and robustly handles ambiguous natural language queries through a unified feature space that balances instance discrimination and ambiguity awareness.

We propose Scene-specific Ambiguity-aware 3D Language Fields (SaaF), a novel Gaussian Splatting-based 3D language field designed for interactive object retrieval in a given real-world scene. Interactive object retrieval using natural language is a crucial capability for service robots operating in complex real-world environments. While recent 3D language field methods for object retrieval establish associations between rendered pixels and autoencoder-compressed CLIP features, they suffer from two limitations: (1) reduced discriminability among similar objects due to feature compression, and (2) poor handling of ambiguous queries, often resulting in unstable or incorrect retrieval. To address these limitations, SaaF introduces a metric learning strategy to construct a unified feature space that is both instance-discriminative and ambiguity-aware. (i) To enhance instance-level visual discrimination, SaaF employs metric learning that pulls image features from multiple viewpoints of the same object closer together in the feature space. (ii) To establish ambiguity awareness, the model jointly trains on multiple text labels generated by the proposed method from each tracked object image sequence, including ambiguous descriptions, to learn the semantic relationships between ambiguous and specific features in a target scene. This feature space enables fine-grained visual understanding while allowing the system to estimate query ambiguity and interactively request clarification when needed. Experimental results demonstrate that SaaF not only improves retrieval accuracy over previous methods but also robustly detects and handles ambiguity in the user text queries under open-vocabulary settings.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes