Papers with Code · CC BY-SA 4.0

ModelNet40

아카이브 평가 111건 · 마지막 적재/변경 2026-10-30

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
PointGST	Overall Accuracy 95.3	Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning 2024-10-10	코드 1
Mamba3D + Point-MAE	Overall Accuracy 95.1 Number of params 16.9M FLOPs 3.9G	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model 2024-04-23	코드 1
ReCon++	Overall Accuracy 95.0	ShapeLLM: Universal 3D Object Understanding for Embodied Interaction 2024-02-27	코드 1 · 코드 2 · 코드 3
PointGPT	Overall Accuracy 94.9	연결 없음 논문 날짜 미기재	연결 없음
point2vec	Overall Accuracy 94.8 Mean Accuracy 92.0	Point2Vec for Self-Supervised Representation Learning on Point Clouds 2023-03-29	코드 1
ULIP + PointMLP	Overall Accuracy 94.7 Mean Accuracy 92.4	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding 2022-12-10	코드 1
ReCon	Overall Accuracy 94.7	Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining 2023-02-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
AsymDSD-B* (no voting)	Overall Accuracy 94.7	Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning 2025-06-26	코드 1
RepSurf-U	Overall Accuracy 94.7 Number of params 1.48M FLOPs 0.81G	Surface Representation for Point Clouds 2022-05-11	코드 1
PointMLP+HyCoRe	Overall Accuracy 94.5 Mean Accuracy 91.9	Rethinking the compositionality of point clouds through regularization in the hyperbolic space 2022-09-21	코드 1
PointMLP	Overall Accuracy 94.5 Mean Accuracy 91.4	Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework 2022-02-15	코드 1
Point-FEMAE	Overall Accuracy 94.5	Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders 2023-12-17	코드 1
OTMae3D	Overall Accuracy 94.5	Rethinking Masked Representation Learning for 3D Point Cloud Understanding 2024-12-26	코드 1
PointNet2+PointCMT	Overall Accuracy 94.4 Mean Accuracy 91.2 Number of params 1.62M	Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis 2022-10-09	코드 1 · 코드 2
IDPT	Overall Accuracy 94.4	Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models 2023-04-14	코드 1 · 코드 2 · 코드 3
OTMae3D (w/o Voting)	Overall Accuracy 94.3	Rethinking Masked Representation Learning for 3D Point Cloud Understanding 2024-12-26	코드 1
IAE + DGCNN	Overall Accuracy 94.2 Mean Accuracy 91.6	Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning 2022-01-03	코드 1
PTv2	Overall Accuracy 94.2 Mean Accuracy 91.6	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling 2022-10-11	코드 1 · 코드 2
CurveNet	Overall Accuracy 94.2	Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis 2021-05-04	코드 1 · 코드 2 · 코드 3
ExpPoint-MAE	Overall Accuracy 94.2	ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers 2023-06-19	코드 1
PCP-MAE	Overall Accuracy 94.2	PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders 2024-08-16	코드 1
RPNet	Overall Accuracy 94.1	Learning Inner-Group Relations on Point Clouds 2021-08-27	코드 1
ULIP + PointBERT	Overall Accuracy 94.1	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding 2022-12-10	코드 1
Point-RAE	Overall Accuracy 94.1	Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning 2023-09-25	코드 1
Point-JEPA (voting)	Overall Accuracy 94.1±0.1	Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud 2024-04-25	코드 1
DeLA	Overall Accuracy 94.0 Mean Accuracy 92.2 Number of params 5.3M FLOPs 1.44G	Decoupled Local Aggregation for Point Cloud Learning 2023-08-31	코드 1
P2P	Overall Accuracy 94.0 Mean Accuracy 91.6	P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting 2022-08-04	코드 1
PointNeXt	Overall Accuracy 94.0 Mean Accuracy 91.1 Number of params 4.5M FLOPs 6.5G	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies 2022-06-09	코드 1 · 코드 2 · 코드 3
Point Voxel Transformer	Overall Accuracy 94.0	PVT: Point-Voxel Transformer for Point Cloud Learning 2021-08-13	코드 1 · 코드 2
Point-MAE	Overall Accuracy 94.0	Masked Autoencoders for Point Cloud Self-supervised Learning 2022-03-13	코드 1 · 코드 2 · 코드 3 · 코드 4