AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Ziyao Zeng, Zipeng Qin, Shanghang Zhang, Peng Gao

ICCV 2023 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 284 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 GPT-3 generated 3D-specific text prompts (ablation)PointCLIP V2 · ModelNet40 zero-shotaccuracy (%): 39.11 -> 64.22Improved
add densify step (local min pooling) (ablation)PointCLIP V2 projection · ModelNet40 zero-shotaccuracy (%): +15.14%Improved
add Gaussian smoothing step (ablation)PointCLIP V2 projection · ModelNet40 zero-shotaccuracy (%): 59.64 -> 64.22Improved
add quantize (voxel grid) step instead of orthogonal projection (ablation)PointCLIP V2 projection · ModelNet40 zero-shotaccuracy (%): 57.35 -> 64.22Improved
use min pooling instead of max or average pooling for densify (ablation)PointCLIP V2 projection · ModelNet40 zero-shotaccuracy (%): 57.35 (max), 60.71 (avg) -> 64.22Improved
add question-answering command to caption command (ablation)GPT prompting · ModelNet40 zero-shotaccuracy (%): 61.67 -> 60.86No clear effect
use all four GPT command types instead of caption only (ablation)GPT prompting · ModelNet40 zero-shotaccuracy (%): 61.67 -> 64.22Improved
make smoothing learnable with 3D conv layers in few-shot setting (ablation)PointCLIP V2 few-shot · ModelNet40 16-shotaccuracy (%): +0.7%Improved
add 3D-specific text in few-shot setting (ablation)PointCLIP V2 few-shot · 16-shotaccuracy (%): +3.33%Improved
increase sampled points from 1024 to 8192 (ablation)PointCLIP V2 · ModelNet40 zero-shotaccuracy (%): 64.22 -> 68.56Improved
use ViT-B/16 backbone instead of other CLIP visual encoders (ablation)PointCLIP V2 · ModelNet40 zero-shotaccuracy (%): 46.45 (RN50) -> 64.22Improved

Later papers that compared with this method

8 later accepted papers report PointCLIPV2 as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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