AI Paper Atlas

Research map / Point clouds / Point cloud classification

CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting

Siyu Jiao, Haoye Dong, Yuyang Yin, Zequn Jie, Yinlong Qian, Yao Zhao, Humphrey Shi, Yunchao Wei

ICCV 2025 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 9 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
fine-tune Uni3D on P&C gaussian attributes (ablation)Uni3D · Objaverse-GSTop1 accuracy: +13.3 Top1, +16.2 Top3, and +15.8 Top5Improved
feed all 3DGS attributes into the network instead of P&C (ablation)fine-tuned Uni3D · Objaverse-GSTop1 accuracy: 46.9 -> 44.8Hurt
add GS Tokenizer (ablation)fine-tuned Uni3D · Objaverse-GSTop1 accuracy: 33.6->47.9 Top1, 52.3->69.9 Top3, and 60.1->76.8 Top5Improved
add image voting loss (ablation)CLIP-GS with GS Tokenizer · Objaverse-GSTop1 accuracy: 47.9 -> 48.5Improved
use multiple ordering strategies instead of one (ablation)CLIP-GS · Objaverse-GSTop1 accuracy: 48.3 -> 48.5No clear effect
initialize from point cloud pretrained weights instead of 2D EVA-CLIP weights (ablation)CLIP-GS · Objaverse-GSTop1 accuracy: 33.9 -> 48.5Improved
unfreeze point cloud pretrained transformer weights (ablation)CLIP-GS · Objaverse-GSTop1 accuracy: 46.6 -> 48.5Improved
scale model from Tiny to Large (ablation)CLIP-GS · Objaverse-GSTop1 accuracy: 45.9 -> 48.8Improved
render 3DGS for 20,000 iterations with SH degree 3 instead of 5,000 iterations with SH degree 0 (ablation)3DGS reconstruction · reconstruction qualityPSNR: 34.6 -> 37.1Improved
use 3DGS input instead of point cloud (Uni3D)CLIP-GS · Objaverse-GS zero-shotTop1 accuracy: 47.7 -> 48.5Improved
use 3DGS input instead of point cloud (Uni3D)CLIP-GS · Text->3D retrievalR@1: 27.8 -> 36.8Improved

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