Papers with Code · CC BY-SA 4.0

Stanford2D3D Panoramic

아카이브 평가 25건 · 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
SFSS-MMSI (RGB+HHA)	mIoU 60.6% mAcc 70.68	Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 2023-08-18	코드 1
SFSS-MMSI (RGB+Depth+Normal)	mIoU 59.43% mAcc 69.03	Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 2023-08-18	코드 1
SFSS-MMSI (RGB+Normal)	mIoU 58.24% mAcc 68.79	Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 2023-08-18	코드 1
SGAT4PASS（RGB only, Fold 1）	mIoU 56.4%	SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation 2023-06-06	코드 1
SFSS-MMSI (RGB+Depth)	mIoU 55.49% mAcc 68.57	Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 2023-08-18	코드 1
SGAT4PASS（RGB only, 3 Fold AVG）	mIoU 55.3%	SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation 2023-06-06	코드 1
Trans4PASS+ (Supervised + Small + MS)	mIoU 54.0%	Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation 2022-07-25	코드 1
Trans4PASS (Supervised + Small + MS)	mIoU 53.0%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 2022-03-02	코드 1
SFSS-MMSI (RGB Only)	mIoU 52.87% mAcc 63.96	Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 2023-08-18	코드 1
Trans4PASS+ (UDA + MPA + MS)	mIoU 52.3%	Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation 2022-07-25	코드 1
CBFC	mIoU 52.2% mAcc 65.6	Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation 2022-07-06	연결 없음
Trans4PASS (Supervised + Small)	mIoU 52.1%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 2022-03-02	코드 1
HoHoNet (ResNet-101)	mIoU 52.0% mAcc 65.0	HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features 2020-11-23	코드 1
Trans4PASS (UDA + MPA + MS)	mIoU 51.2%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 2022-03-02	코드 1
Trans4PASS (UDA + MPA)	mIoU 50.8%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 2022-03-02	코드 1
PanoFormer	mIoU 48.9% mAcc 64.5	PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation 2022-03-17	코드 1
Trans4PASS (UDA + Source Only)	mIoU 48.1%	Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 2022-03-02	코드 1
FreDSNet	mIoU 46.1% mAcc 63.1	FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions 2022-10-04	코드 1
Tangent (ResNet-101)	mIoU 45.6% mAcc 65.2	Tangent Images for Mitigating Spherical Distortion 2019-12-19	코드 1
SWSCNN	mIoU 43.4%	Spin-Weighted Spherical CNNs 2020-06-18	코드 1 · 코드 2
HexRUNet	mIoU 43.3% mAcc 58.6	Orientation-aware Semantic Segmentation on Icosahedron Spheres 2019-07-30	코드 1
Interpolated SelectionConv	mIoU 41.4%	Interpolated SelectionConv for Spherical Images and Surfaces 2022-10-18	코드 1
GaugeNet (R2R-U-Net)	mIoU 39.4% mAcc 55.9	Gauge Equivariant Convolutional Networks and the Icosahedral CNN 2019-02-11	코드 1 · 코드 2
UGSCNN	mIoU 38.3% mAcc 54.65	Spherical CNNs on Unstructured Grids 2019-01-07	코드 1
DisConv	mIoU 34.6%	Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images 2018-09-01	연결 없음