Research map / Point clouds / Point cloud classification
Text2Loc++: Generalizing 3D Point Cloud Localization From Natural Language
Yan Xia, Letian Shi, Yilin Di, Joao F. Henriques, Daniel Cremers
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add masked instance training (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 32.1 -> 35.3 | Improved |
| keep only described instances instead of masked instance training (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 35.3 -> 10.1 | Hurt |
| add submap loss in modality-aware contrastive learning (ablation) | Text2Loc++ · KITTI360Pose | recall@1: 32.5 -> 35.3 | Improved |
| add instance loss (ablation) | Text2Loc++ · KITTI360Pose | recall@1: 33.2 -> 35.3 | Improved |
| add text loss (ablation) | Text2Loc++ · KITTI360Pose | recall@1: 33.4 -> 35.3 | Improved |
| add text distillation for complex text (ablation) | Text2Loc++ · KITTI360Pose complex text | recall@1: 19.0 -> 27.9 | Improved |
| add text distillation for moderate text (ablation) | Text2Loc++ · KITTI360Pose moderate text | recall@1: 22.7 -> 34.0 | Improved |
| simplify complex text with ChatGPT-4o before encoding (ablation) | Text2Loc++ · KITTI360Pose complex text | recall@1 | No clear effect |
| replace InfoNCE with pairwise ranking loss (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 35.3 -> 31.5 | Hurt |
| add hierarchical transformer module (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 31.0 -> 35.3 | Improved |
| use inter-mean instead of max pooling (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 35.3 -> 32.0 | Hurt |
| swap T5-large text backbone for Llama3.2-1B (ablation) | Text2Loc++ · KITTI360Pose submap retrieval | recall@1: 35.3 -> 33.2 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Text2Loc — Text2Loc: 3D Point Cloud Localization from Natural Language (CVPR 2024) · better on 11 of 11 shared results
- CMMLoc — CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework (CVPR 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Text2Loc: 3D Point Cloud Localization from Natural Language (CVPR 2024 · similarity 0.95)
- Text to Point Cloud Localization with Multi-Level Negative Contrastive Learning (AAAI 2025 · similarity 0.91)
- CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework (CVPR 2025 · similarity 0.90)
- More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding (AAAI 2025 · similarity 0.88)
- Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models (NeurIPS 2025 · similarity 0.86)
- LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
