← Zero-Shot Transfer 3D Point Cloud Classification

Papers with Code · CC BY-SA 4.0

ModelNet40

아카이브 평가 16건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
Uni3D	Accuracy (%) 88.2	Uni3D: Exploring Unified 3D Representation at Scale 2023-10-10	코드 1 · 코드 2
ViT-Lens	Accuracy (%) 87.6	ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights 2023-08-20	코드 1
ReCon++	Accuracy (%) 87.3	ShapeLLM: Universal 3D Object Understanding for Embodied Interaction 2024-02-27	코드 1 · 코드 2 · 코드 3
MixCon3D-PointBERT	Accuracy (%) 86.8	Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training 2023-11-03	코드 1
TAMM-PointBERT (+dlign)	Accuracy (%) 86.2	OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images 2024-04-25	코드 1
OpenShape-PointBERT (+dlign)	Accuracy (%) 85.4	OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images 2024-04-25	코드 1
OpenShape-PointBERT	Accuracy (%) 85.3	OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding 2023-05-18	코드 1
OpenShape-SparseConv (+dlign)	Accuracy (%) 85.0	OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images 2024-04-25	코드 1
OpenShape-SparseConv	Accuracy (%) 83.4	OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding 2023-05-18	코드 1
OpenDlign	Accuracy (%) 82.6	OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images 2024-04-25	코드 1
PointCLIP V2	Accuracy (%) 64.22	PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning 2022-11-21	코드 1 · 코드 2
ReCon	Accuracy (%) 61.7	Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining 2023-02-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
ULIP + PointMLP	Accuracy (%) 61.5	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding 2022-12-10	코드 1
ULIP + PointBERT	Accuracy (%) 60.4	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding 2022-12-10	코드 1
CLIP2Point	Accuracy (%) 49.38	CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training 2022-10-03	코드 1
PointCLIP	Accuracy (%) 20.18	PointCLIP: Point Cloud Understanding by CLIP 2021-12-04	코드 1 · 코드 2