AI Paper Atlas

Research map / 3D vision / 3D generation

A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation

Wentao Qu, Guofeng Mei, Yang Wu, YongShun Gong, Xiaoshui Huang, Liang Xiao

CVPR 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 3 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 SCRG and DPE to text-guided T2LDM (ablation)T2LDM · nuScenes text-guidedFSVD / TBR: FSVD 73.64 -> 66.93; TBR 19.32 -> 23.44Improved
add SCRG alone (without DPE) (ablation)T2LDM baseline · nuScenes text-guidedFSVD: 73.64 -> 68.45Improved
add DPE alone (without SCRG) (ablation)T2LDM baseline · nuScenes text-guidedFSVD: 73.64 -> 71.32Improved
add SCRG for faster convergence (ablation)T2LDM (DPE only) · KITTI-360 at 30k iterationsFSVD: 91.32 -> 47.29Improved
train guidance network end-to-end rather than pretrained (ablation)SCRG · nuScenesFSVD: 68.77 -> 64.21Improved
pretrain the guidance network instead of no guidance (ablation)T2LDM (DPE only) · nuScenesFSVD: 68.11 -> 68.77Hurt
use explicit location text prompt (ablation)T2LDM · nuScenes text promptsTBR (%): TBR 12.23 vs 31.12 for 'Two cars.'Hurt
use longer prompts with similar semantics (ablation)T2LDM · nuScenes text promptsFSID / TBR: FSID 67.32 -> 67.63; TBR 31.12 -> 29.88Hurt
use different prompt form at inference than training (ablation)T2LDM · nuScenes text promptsTBR (%): 31.12 -> 29.23No clear effect
adjust location text to sample-distribution-aware form (ablation)T2LDM prompts · nuScenes text promptsTBR (%): 12.23 -> 23.42Improved
adjust quantity text (less/more than five cars) (ablation)T2LDM prompts · nuScenes text promptsTBR (%): 31.12 -> 60.35Improved
add directional position encodingT2LDM · nuScenesstreet distortionImproved

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