AI Paper Atlas

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

ECCV 2024 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals

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
replace Text2LiDAR with R2DM for uncontrolled generation (FPD)Text2LiDAR · KITTI-360 uncontrolled generationFPD: 6.24 -> 4.81Improved
Text2LiDAR versus R2DM on FRDText2LiDAR · KITTI-360 uncontrolled generationFRD: 149.66 -> 164.16Hurt
add equirectangular attention (EA) and reverse EA (REA) in place of plain self-attention (ablation)Text2LiDAR · KITTI-360 ablationFPD: 10.52 -> 4.81Improved
add REA (ablation)Text2LiDAR · KITTI-360 ablationFPD: 8.02 -> 4.81Improved
add EA (ablation)Text2LiDAR · KITTI-360 ablationFPD: 7.41 -> 4.81Improved
use CEI instead of channel-wise concatenation (ablation)Text2LiDAR · KITTI-360 ablationFPD: 6.99 -> 4.81Improved
add frequency modulator (FM) (ablation)Text2LiDAR · KITTI-360 ablationFPD: 5.95 -> 4.81Improved
add FM (ablation)Text2LiDAR · KITTI-360 ablationFRD: 165.33 -> 164.16Improved
increase decoder layers from 3 to 4 (ablation)Text2LiDAR · KITTI-360 ablationFPD: 19.36 -> 4.81Improved
use Text2LiDAR instead of R2DM for densificationRepaint-based densification · KITTI-360 densification (90% points removed)Semantic IoU %: 40.16 -> 41.37Improved
use transformer Text2LiDAR with text control instead of R2DM U-Net32-beam generation · generation timetime (s): 7.79 -> 4.57Improved

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.

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