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
OmniVec2	Mean IoU 63.6	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning 2024-01-01	연결 없음
DiffusionMMS (DAT++-S)	Mean IoU 61.5	Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer 2024-09-23	연결 없음
DepthMatch (DINOv2-S)	Mean IoU 61.4	DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization 2025-05-26	연결 없음
GeminiFusion (Swin-Large)	Mean IoU 60.2	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
OmniVec	Mean IoU 60.8	OmniVec: Learning robust representations with cross modal sharing 2023-11-07	연결 없음
DPLNet	Mean IoU 59.3	Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning 2023-12-01	코드 1
HDBFormer	Mean IoU 59.3%	HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework 2025-04-18	코드 1
EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)	Mean IoU 59.02	PanopticNDT: Efficient and Robust Panoptic Mapping 2023-09-24	코드 1 · 코드 2 · 코드 3 · 코드 4
DFormerv2-L	Mean IoU 58.4%	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
SwinMTL	Mean IoU 58.14%	SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images 2024-03-15	코드 1
PolyMaX(ConvNeXt-L)	Mean IoU 58.08%	PolyMaX: General Dense Prediction with Mask Transformer 2023-11-09	코드 1
HSPFormer(PVT v2-B4)	Mean IoU 57.8%	HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation 2025-01-16	코드 1
GeminiFusion (MiT-B5)	Mean IoU 57.7	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
DFormerv2-B	Mean IoU 57.7%	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
DFormer-L	Mean IoU 57.2%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
CMX (B5)	Mean IoU 56.9%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
CMNeXt (B4)	Mean IoU 56.9%	Delivering Arbitrary-Modal Semantic Segmentation 2023-03-02	코드 1
OMNIVORE (Swin-L, finetuned)	Mean IoU 56.8%	Omnivore: A Single Model for Many Visual Modalities 2022-01-20	코드 1 · 코드 2
GeminiFusion (MiT-B3)	Mean IoU 56.8	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 2024-06-03	코드 1
CMX (B4)	Mean IoU 56.3%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
MultiMAE (ViT-B)	Mean IoU 56.0%	MultiMAE: Multi-modal Multi-task Masked Autoencoders 2022-04-04	코드 1
DFormerv2-S	Mean IoU 56.0%	DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 2025-04-07	코드 1
SMMCL (SegNeXt-B)	Mean IoU 55.8%	Understanding Dark Scenes by Contrasting Multi-Modal Observations 2023-08-23	코드 1
DFormer-B	Mean IoU 55.6%	DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation 2023-09-18	코드 1
ComPtr (Swin-B)	Mean IoU 55.5%	ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer 2023-07-23	코드 1
AsymFormer	Mean IoU 55.3%	AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation 2023-09-25	코드 1
OMNIVORE (Swin-B, finetuned)	Mean IoU 55.1%	Omnivore: A Single Model for Many Visual Modalities 2022-01-20	코드 1 · 코드 2
HAPNet	Mean IoU 55.0 Mean Accuracy 68.8	HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion 2024-04-04	코드 1
CMX (B2)	Mean IoU 54.4%	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 2022-03-09	코드 1
TokenFusion (S)	Mean IoU 54.2%	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