AI Paper Atlas

Research map / Point clouds / Point cloud classification

CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation

Mainak Singha, Sarthak Mehrotra, Paolo Casari, Subhasis Chaudhuri, Elisa Ricci, Biplab Banerjee

CVPR 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 3 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
apply CLIPoint3D (LoRA on vision encoder + prompt tuning) instead of encoder-based 3D UDACLIP ViT-B/16 · PointDA-10 avgaccuracy (%): 72.2 -> 75.7Improved
adapt CLIP with CLIPoint3D versus best encoder-based baselineCLIP ViT-B/16 · GraspNetPC-10 avgaccuracy (%): 75.8 -> 92.2Improved
CLIPoint3D on ScanNet target directionsCLIP ViT-B/16 · PointDA-10 ModelNet->ScanNetaccuracy (%): 57.1 -> 53.5Hurt
apply LoRA to text encoder only (CLIPoint3D-T) (ablation)CLIPoint3D · PointDA-10 avgaccuracy (%): 50.7 vs 75.7 (vision)Hurt
add LoRA on vision encoder in addition to prompt tuning (ablation)CLIPoint3D (GraspNetPC-10) · GraspNetPC-10 avgaccuracy (%): 78.9 -> 90.7Improved
add knowledge-driven prompt tuning to LoRA on both encoders (ablation)CLIPoint3D (GraspNetPC-10) · GraspNetPC-10 avgaccuracy (%): 90.5 -> 92.2Improved
use LoRA instead of LayerNorm tuning or BitFit (ablation)CLIPoint3D · GraspNetPC-10 avgaccuracy (%): LoRA 90.5 vs BitFit 81.1 vs LayerNorm 76.6Improved
add OT alignment loss to Lce+Lortho (ablation)CLIPoint3D · PointDA-10 avgaccuracy (%): 58.6 -> 70.4Improved
add prototype alignment loss to Lce+Lortho (ablation)CLIPoint3D · PointDA-10 avgaccuracy (%): 58.6 -> 64.5Improved
add all alignment losses (proto, OT, conf) to Lce+Lortho (ablation)CLIPoint3D · GraspNetPC-10 avgaccuracy (%): 74.9 -> 92.2Improved
use LLM-guided text prompt and 3D-conditioned visual prompt instead of plain learned prompts (ablation)CLIPoint3D · PointDA-10 avgaccuracy (%): 72.4 -> 75.7Improved
replace entropy-guided view selection with random single view (ablation)CLIPoint3D-B · GraspNetPC-10accuracy (%): 70.9 -> 92.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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