Papers with Code · CC BY-SA 4.0

NYU Depth v2

아카이브 평가 120건 · 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
HaarNet	Mean IoU 50.7%	HaarNet: Large-scale Linear-Morphological Hybrid Network for RGB-D Semantic Segmentation 2023-10-11	연결 없음
PAP (ResNet-50)	Mean IoU 50.4%	Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation 2019-06-08	연결 없음
Cerberus	Mean IoU 50.4%	Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing 2021-11-24	코드 1
ESANet (R34-NBt1D)	Mean IoU 50.30	Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis 2020-11-13	코드 1 · 코드 2 · 코드 3 · 코드 4
Z-ACN (ResNet-50)	Mean IoU 50.05%	Depth-Adapted CNNs for RGB-D Semantic Segmentation 2022-06-08	연결 없음
Malleable 2.5D (ResNet-50)	Mean IoU 49.7%	Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing 2020-07-18	코드 1 · 코드 2
MMANet	Mean IoU 49.62%	MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning 2023-04-17	코드 1
SGACNet (R34-NBt1D)	Mean IoU 49.4%	Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation 2023-08-11	코드 1
ComPtr (Swin-T)	Mean IoU 49.2%	ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer 2023-07-23	코드 1
Z-ACN (ResNet-34)	Mean IoU 49.15%	Depth-Adapted CNNs for RGB-D Semantic Segmentation 2022-06-08	연결 없음
UMT	Mean IoU 49.14%	Improving Multi-Modal Learning with Uni-Modal Teachers 2021-06-21	연결 없음
MTI-Net (HRNet-48)	Mean IoU 49.0	MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning 2020-01-19	코드 1
ShapeConv (ResNet-101)	Mean IoU 49.0%	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation 2021-08-24	코드 1
MKE	Mean IoU 48.88%	Multimodal Knowledge Expansion 2021-03-26	코드 1
ShapeConv (ResNet-50)	Mean IoU 48.8%	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation 2021-08-24	코드 1
mmFormer	Mean IoU 48.45%	mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation 2022-06-06	코드 1
ACNet	Mean IoU 48.3%	ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation 2019-05-24	코드 1
SGACNet (R18-NBt1D)	Mean IoU 48.2%	Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation 2023-08-11	코드 1
ESANet (R18-NBt1D )	Mean IoU 48.17	Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis 2020-11-13	코드 1 · 코드 2 · 코드 3 · 코드 4
RFNet	Mean IoU 48.13%	RFNet: Region-Aware Fusion Network for Incomplete Multi-Modal Brain Tumor Segmentation 2021-01-01	코드 1
TupleInfoNCE	Mean IoU 48.1%	Contrastive Multimodal Fusion with TupleInfoNCE 2021-07-06	코드 1
DDSC (ResNet-101)	Mean IoU 48.1%	Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation 2018-06-01	연결 없음
CFN	Mean IoU 47.7%	Cascaded Feature Network for Semantic Segmentation of RGB-D Images 2017-10-01	연결 없음
FDNet (DenseNet264)	Mean IoU 47.4%	Learning Fully Dense Neural Networks for Image Semantic Segmentation 2019-05-22	연결 없음
RedNet	Mean IoU 47.2%	RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation 2018-06-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
Z-ACN (ResNet-18)	Mean IoU 47.02%	Depth-Adapted CNNs for RGB-D Semantic Segmentation 2022-06-08	연결 없음
TRL (ResNet-101)	Mean IoU 46.8%	Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation 2018-09-01	연결 없음
RefineNet (ResNet-101)	Mean IoU 46.5%	RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation 2016-11-20	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13
PGT (Swin-S)	Mean IoU 46.43	Prompt Guided Transformer for Multi-Task Dense Prediction 2023-07-28	코드 1
ATRC	Mean IoU 46.33%	Exploring Relational Context for Multi-Task Dense Prediction 2021-04-28	코드 1