AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding

Runyu Ding, Jihan Yang, Chuhui Xue, Wenqing Zhang, Song Bai, Xiaojuan Qi

CVPR 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 124 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 image-bridged point-caption supervision (ablation)PLA · ScanNet semantic B15/N4hIoU: 39.7 -> 65.3Improved
add binary calibration head (ablation)LSeg-3D · ScanNet semantic B15/N4hIoU: 00.0 -> 39.8Improved
add entity-level caption supervision (ablation)PLA with binary calibration · ScanNet semantic B15/N4hIoU: 39.8 -> 63.6Improved
add view-level caption supervision (ablation)PLA with binary calibration · ScanNet semantic B15/N4hIoU: 39.8 -> 61.3Improved
add scene-level caption supervision to view- and entity-level captions (ablation)PLA with binary calibration and view/entity captions · ScanNet semantic B15/N4hIoU: 65.3 -> 64.6Hurt
retain only entity phrases in generated captions (ablation)PLA · ScanNet semantic B15/N4hIoU: 65.3 -> 65.7Improved
use only category label names in captions rather than diverse entity phrases (ablation)PLA · ScanNet semantic B15/N4mIoU novel: 62.4 -> 49.6Hurt
replace CLIP with BERT as text encoder (ablation)PLA · ScanNet semantic B15/N4mIoU novel: 62.4 -> 55.2Hurt
replace ViT-GPT2 with OFA for image captioning (ablation)PLA · ScanNet semantic B15/N4hIoU: 65.3 -> 65.6Improved
add self-training with novel-category namesPLA · ScanNet semantic B15/N4hIoU: 65.3 -> 70.3Improved
add point-caption supervision to a fully supervised model (ablation)Fully-Sup. · ScanNet semantic B15/N4mIoU: 70.62 -> 70.82No clear effect

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