AI Paper Atlas

Research map / Point clouds / Point cloud classification

Any2Point: Empowering Any-modality Transformers for Efficient 3D Understanding

Yiwen Tang, Ray Zhang, Jiaming Liu, Zoey Guo, Bin Zhao, Zhigang Wang, Dong Wang, Peng Gao, Hongsheng Li, Xuelong Li

ECCV 2024 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D

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 3D-to-any virtual projection positional encoding (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 88.7 -> 89.3Improved
add any-to-3D guided adapter (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 88.7 -> 90.9Improved
add both virtual projection and guided adapter (ablation)Any2Point (DINO V2) · ScanObjectNN PB-T50-RSaccuracy (%): 86.1 -> 87.7Improved
use sinusoidal or learnable PE instead of no PE (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 90.9 -> 87.4 (sinusoidal), 90.5 (learnable)Hurt
use virtual projection PE instead of learnable PE (ablation)Any2Point (DINO V2) · ScanObjectNN PB-T50-RSaccuracy (%): 86.5 -> 87.7Improved
add 1D/2D-guided local aggregation to adapter (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 89.3 -> 90.2Improved
add adaptive any-to-3D ensemble (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 90.2 -> 91.9Improved
use guided adapter instead of LoRA (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 86.3 -> 91.9Improved
use guided adapter PEFT instead of full fine-tuning (ablation)Any2Point (CLIP-Text) · ScanObjectNN PB-T50-RSaccuracy (%): 79.9 -> 91.9Improved
use language (1D) source model instead of 2D vision or audioAny2Point · ScanObjectNN PB-T50-RSaccuracy (%): 87.7 -> 91.9Improved

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