AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point Cloud Quantization Through Multimodal Prompting for 3D Understanding

Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu

AAAI 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 1 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 compactness loss to alignment loss (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 69.95 -> 70.01No clear effect
add separation loss alone to alignment loss (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 69.95 -> 69.19Hurt
use both compactness and separation losses together (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 69.95 -> 71.03Improved
add point cloud adapter (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 56.73 -> 71.03Improved
add learnable prompts (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 67.66 -> 71.03Improved
add quantization module (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 67.59 -> 71.03Improved
learnable prompts instead of handcrafted template (ablation)PCQ prototypes · ScanObjectNN PB 8-shotaccuracy (%): 69.19 -> 71.03Improved
handcrafted template instead of bare class name (ablation)PCQ prototypes · ScanObjectNN PB 8-shotaccuracy (%): 67.66 -> 69.19Improved
text embeddings as prototypes instead of cluster centroids (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 69.60 -> 71.03Improved
text embeddings as prototypes instead of trainable codebooks (ablation)PCQ · ScanObjectNN PB 8-shotaccuracy (%): 70.06 -> 71.03Improved
PCQ on Uni3D-Ti backbone vs standard PEFTUni3D-Ti · ScanObjectNN PB few-shotaccuracy (%): +5.10 (1-shot) to +0.35 (8-shot)Improved
apply PCQ vs PPT, trained on OBJ and tested on BGULIP-2 · ScanObjectNN OBJ->BGaccuracy (%): 83.2 -> 86.9Improved

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