AI Paper Atlas

Research map / Point clouds / Point cloud classification

3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

Junyu Luo, Jiahui Fu, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu

CVPR 2022 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 84 citations (OpenAlex)

Check 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
Use single-stage progressive referred-point selection3D-SPS · ScanRefer Overall, 3D onlyAcc@0.5: 34.47 -> 36.43Improved
Use single-stage progressive referred-point selection3D-SPS · ScanRefer Overall, 2D + 3DAcc@0.5: 34.67 -> 36.98Improved
Use TPM progressive selection3D-SPS · Nr3D Overallaccuracy: +2.3%Improved
Use TPM progressive selection3D-SPS · Sr3D Overallaccuracy: +4.7%Improved
Add description relevance score s_d to DKS (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 34.95 -> 36.43Improved
Add object confidence score s_o to DKS (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 35.19 -> 36.43Improved
Replace FPS with DKS (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 31.88 -> 36.43Improved
Use 4 TPM layers rather than 1, 2, or 3 (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 33.13, 33.97, 34.53 -> 36.43Improved
Increase TPM depth from 4 to 5 layers (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 36.43 -> 36.07Hurt
Add progressive keypoint selection, reducing 512 keypoints to 32 (ablation)3D-SPS on ScanRefer · ScanRefer Overall, 3D onlyAcc@0.5: 34.98 -> 36.43Improved
Use 3D-SPS on Sr3D Easy rather than LanguageRefer3D-SPS · Sr3D Easyaccuracy: 58.9% -> 56.2% ± 0.6%Hurt

Later papers that compared with this method

3 later accepted papers report 3D-SPS as a baseline in their results tables; 3 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