Papers with Code · CC BY-SA 4.0

SUN-RGBD

아카이브 평가 44건 · 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
GeminiFusion (Swin-Large)	Mean IoU 54.6	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
DiffusionMMS	Mean IoU 54.0	Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer 2024-09-23	연결 없음
HDBFormer	Mean IoU 53.9%	HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework 2025-04-18	코드 1
GeminiFusion (MiT-B5)	Mean IoU 53.3	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
DFormerv2-L	Mean IoU 53.3	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
TokenFusion (S)	Mean IoU 53.0%	Multimodal Token Fusion for Vision Transformers 2022-04-19	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
DPLNet	Mean IoU 52.8%	Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning 2023-12-01	코드 1
DFormerv2-B	Mean IoU 52.8%	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
GeminiFusion (MiT-B3)	Mean IoU 52.7	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
DFormer-L	Mean IoU 52.5%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
CMX (B5)	Mean IoU 52.4%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
CMX (B4)	Mean IoU 52.1%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
DFormerv2-S	Mean IoU 51.5%	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
TokenFusion (Ti)	Mean IoU 51.4%	Multimodal Token Fusion for Vision Transformers 2022-04-19	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
DFormer-B	Mean IoU 51.2%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)	Mean IoU 50.86%	PanopticNDT: Efficient and Robust Panoptic Mapping 2023-09-24	코드 1 · 코드 2 · 코드 3 · 코드 4
FSFNet	Mean IoU 50.6%	Deep feature selection-and-fusion for RGB-D semantic segmentation 2021-05-10	연결 없음
PSD-ResNet50	Mean IoU 50.6%	Pattern-Structure Diffusion for Multi-Task Learning 2020-06-01	연결 없음
TokenFusion (S)	Mean IoU 50.0%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
DPLNet	Mean IoU 49.7%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
DFormer-L	Mean IoU 49.6%	Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation 2022-01-05	연결 없음
CMX (B5)	Mean IoU 49.6%	DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation 2022-10-13	연결 없음
CMX (B4)	Mean IoU 49.6%	Pixel Difference Convolutional Network for RGB-D Semantic Segmentation 2023-02-23	연결 없음
TokenFusion (Ti)	Mean IoU 49.4%	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation 2020-07-17	코드 1 · 코드 2
DFormer-B	Mean IoU 49.1%	AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation 2023-09-25	코드 1
EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)	Mean IoU 48.82%	Efficient Multi-Task Scene Analysis with RGB-D Transformers 2023-06-08	코드 1 · 코드 2
FSFNet	Mean IoU 48.8%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
PSD-ResNet50	Mean IoU 48.6%	ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation 2021-08-24	코드 1
TokenFusion (S)	Mean IoU 48.6%	Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation 2020-04-09	코드 1
DPLNet	Mean IoU 48.47%	Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments 2022-07-10	코드 1 · 코드 2