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