Papers with Code · CC BY-SA 4.0

ScanObjectNN

아카이브 평가 77건 · 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
OTMae3D	Overall Accuracy 89.0 FLOPs 6.29 OBJ-BG (OA) 92.9 OBJ-ONLY (OA) 92.3	Rethinking Masked Representation Learning for 3D Point Cloud Understanding 2024-12-26	코드 1
ULIP-2 + Point-BERT	Overall Accuracy 89.0	ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding 2023-05-14	코드 1
PointNeXt+Local	Overall Accuracy 88.6 Mean Accuracy 87.4	Local Neighborhood Features for 3D Classification 2022-12-09	코드 1
SPoTr	Overall Accuracy 88.6 Mean Accuracy 86.8	Self-positioning Point-based Transformer for Point Cloud Understanding 2023-03-29	코드 1
IDPT	Overall Accuracy 88.51 OBJ-BG (OA) 93.12	Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models 2023-04-14	코드 1 · 코드 2 · 코드 3
PointMLP+TAP	Overall Accuracy 88.5	Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models 2023-07-27	코드 1
PointNeXt+GAM	Overall Accuracy 88.4 Number of params 1.4M FLOPs 1.64G	$(0, 4)$ dualities 2015-12-14	연결 없음
PointNeXt+HyCoRe	Overall Accuracy 88.3 Mean Accuracy 87.0	Rethinking the compositionality of point clouds through regularization in the hyperbolic space 2022-09-21	코드 1
ACT (no voting)	Overall Accuracy 88.21 OBJ-BG (OA) 93.29 OBJ-ONLY (OA) 91.91	Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning? 2022-12-16	코드 1 · 코드 2 · 코드 3 · 코드 4
PointNeXt	Overall Accuracy 88.2 Mean Accuracy 86.8 Number of params 1.4M FLOPs 1.64G	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies 2022-06-09	코드 1 · 코드 2 · 코드 3
PointConT (no voting)	Overall Accuracy 88.0 Mean Accuracy 86.0	Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space 2023-03-08	코드 1
PointVector-S	Overall Accuracy 87.8 Mean Accuracy 86.2	PointVector: A Vector Representation In Point Cloud Analysis 2022-05-21	코드 1
point2vec	Overall Accuracy 87.5 Mean Accuracy 86.0 OBJ-BG (OA) 91.2 OBJ-ONLY (OA) 90.4	Point2Vec for Self-Supervised Representation Learning on Point Clouds 2023-03-29	코드 1
PointStack	Overall Accuracy 87.2 Mean Accuracy 86.2	Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling 2022-05-20	코드 1 · 코드 2
Point-PN	Overall Accuracy 87.1 Number of params 0.8M	Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis 2023-03-14	코드 1 · 코드 2 · 코드 3
PointCMT	Overall Accuracy 86.7 Mean Accuracy 84.8 Number of params 12.6M	Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis 2022-10-09	코드 1 · 코드 2
Point-JEPA	Overall Accuracy 86.6 OBJ-BG (OA) 92.9±0.4	Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud 2024-04-25	코드 1
PointMLS	Overall Accuracy 86.6	ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification 2024-01-16	코드 1
Point-M2AE	Overall Accuracy 86.43 OBJ-BG (OA) 91.22 OBJ-ONLY (OA) 88.81	Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training 2022-05-28	코드 1 · 코드 2 · 코드 3
ULIP + PointBERT	Overall Accuracy 86.4	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding 2022-12-10	코드 1
DualMLP	Overall Accuracy 86.4	DualMLP: a two-stream fusion model for 3D point cloud classification 2023-10-10	코드 1
RepSurf-U (2x)	Overall Accuracy 86.0 Number of params 6.80M FLOPs 2.43G	Surface Representation for Point Clouds 2022-05-11	코드 1
PointMLP	Overall Accuracy 85.7 Mean Accuracy 84.4	Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework 2022-02-15	코드 1
Point-LGMask	Overall Accuracy 85.3 OBJ-BG (OA) 89.8 OBJ-ONLY (OA) 89.3	Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking 2023-06-08	코드 1
Point-MAE	Overall Accuracy 85.2 OBJ-BG (OA) 90.02 OBJ-ONLY (OA) 88.29	Masked Autoencoders for Point Cloud Self-supervised Learning 2022-03-13	코드 1 · 코드 2 · 코드 3 · 코드 4
MVTN+SimpleView++	Overall Accuracy 84.8	SimpleView++: Neighborhood Views for Point Cloud Classification 2022-09-08	코드 1
DeltaConv	Overall Accuracy 84.7	DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds 2021-11-16	코드 1
RepSurf-U	Overall Accuracy 84.6 Number of params 1.48M FLOPs 0.81G	Surface Representation for Point Clouds 2022-05-11	코드 1
APP-Net	Overall Accuracy 84.1	APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification 2022-05-02	코드 1
PointMLP-elite	Overall Accuracy 83.8 Mean Accuracy 81.8	Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework 2022-02-15	코드 1