AI Paper Atlas

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

TPAMI 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add masked instance training (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 32.1 -> 35.3Improved
keep only described instances instead of masked instance training (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 35.3 -> 10.1Hurt
add submap loss in modality-aware contrastive learning (ablation)Text2Loc++ · KITTI360Poserecall@1: 32.5 -> 35.3Improved
add instance loss (ablation)Text2Loc++ · KITTI360Poserecall@1: 33.2 -> 35.3Improved
add text loss (ablation)Text2Loc++ · KITTI360Poserecall@1: 33.4 -> 35.3Improved
add text distillation for complex text (ablation)Text2Loc++ · KITTI360Pose complex textrecall@1: 19.0 -> 27.9Improved
add text distillation for moderate text (ablation)Text2Loc++ · KITTI360Pose moderate textrecall@1: 22.7 -> 34.0Improved
simplify complex text with ChatGPT-4o before encoding (ablation)Text2Loc++ · KITTI360Pose complex textrecall@1No clear effect
replace InfoNCE with pairwise ranking loss (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 35.3 -> 31.5Hurt
add hierarchical transformer module (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 31.0 -> 35.3Improved
use inter-mean instead of max pooling (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 35.3 -> 32.0Hurt
swap T5-large text backbone for Llama3.2-1B (ablation)Text2Loc++ · KITTI360Pose submap retrievalrecall@1: 35.3 -> 33.2No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy