Research map / Point clouds / Shape and surface completion
Text2LiDAR: Text-guided LiDAR Point Clouds Generation via Equirectangular Transformer
Yang Wu, Kaihua Zhang, Jianjun Qian, Jin Xie, Jian Yang
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 |
|---|---|---|---|
| replace Text2LiDAR with R2DM for uncontrolled generation (FPD) | Text2LiDAR · KITTI-360 uncontrolled generation | FPD: 6.24 -> 4.81 | Improved |
| Text2LiDAR versus R2DM on FRD | Text2LiDAR · KITTI-360 uncontrolled generation | FRD: 149.66 -> 164.16 | Hurt |
| add equirectangular attention (EA) and reverse EA (REA) in place of plain self-attention (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 10.52 -> 4.81 | Improved |
| add REA (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 8.02 -> 4.81 | Improved |
| add EA (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 7.41 -> 4.81 | Improved |
| use CEI instead of channel-wise concatenation (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 6.99 -> 4.81 | Improved |
| add frequency modulator (FM) (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 5.95 -> 4.81 | Improved |
| add FM (ablation) | Text2LiDAR · KITTI-360 ablation | FRD: 165.33 -> 164.16 | Improved |
| increase decoder layers from 3 to 4 (ablation) | Text2LiDAR · KITTI-360 ablation | FPD: 19.36 -> 4.81 | Improved |
| use Text2LiDAR instead of R2DM for densification | Repaint-based densification · KITTI-360 densification (90% points removed) | Semantic IoU %: 40.16 -> 41.37 | Improved |
| use transformer Text2LiDAR with text control instead of R2DM U-Net | 32-beam generation · generation time | time (s): 7.79 -> 4.57 | Improved |
Later papers that compared with this method
3 later accepted papers report Text2LiDAR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Structure-to-Intensity Diffusion for Adverse-Weather LiDAR Generation (CVPR 2026 · better on 0 of 1 shared result)
- DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving (AAAI 2026 · better on 1 of 1 shared result)
- WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion (CVPR 2025 · better on 1 of 2 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
- WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion (CVPR 2025 · similarity 0.86)
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance (NeurIPS 2026 · similarity 0.86)
- LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding (AAAI 2025 · similarity 0.85)
- GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds (CVPR 2024 · similarity 0.85)
- TULIP: Transformer for Upsampling of LiDAR Point Clouds (CVPR 2024 · similarity 0.85)
- Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding (NeurIPS 2025 · similarity 0.85)
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.
