PardisTaghavi / SwinMTL
A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images
☆24Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for SwinMTL
- [ITSC-2023] HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection☆32Updated last year
- The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.☆105Updated last year
- [ECCV 2024] SDK for MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty☆30Updated 4 months ago
- The official Implementation of "VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection" [CVPR 202…☆36Updated 6 months ago
- [ICCV 2023] Official PyTorch implementation of our paper SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Aut…☆18Updated last year
- Official implementation for "AllWeatherNet:Unified Image enhancement for autonomous driving under adverse weather and lowlight-conditions…☆24Updated 3 weeks ago
- ☆37Updated last month
- ☆15Updated last month
- Source code for "To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation", ICCV 2023☆48Updated 5 months ago
- Official implementation of Dense Prediction with Attentive Feature Aggregation, WACV 2023☆12Updated last year
- Unsupervised condition-level adaptation for semantic segmentation☆21Updated 4 months ago
- Official implementation for the ICASSP 2024 paper "Building Lane-Level Maps from Aerial Images"☆26Updated 6 months ago
- Finetuning DINOv2 (https://github.com/facebookresearch/dinov2) on your own dataset☆38Updated last year
- ES³Net: Accurate and Efficient Edge-Based Self-Supervised Stereo Matching Network (CVPRW2023)☆23Updated last year
- [ECCV2024] Occlusion-Aware Seamless Segmentation☆20Updated 2 months ago
- Repository of DELIVER dataset and CMNeXt models (CVPR 2023)☆149Updated 3 months ago
- This is the official GitHub page of the Multi-Spectral Stereo (MS2) dataset described in CVPR 2023 paper.☆58Updated 10 months ago
- [CVPR2024] Open-world Semantic Segmentation Including Class Similarity☆66Updated 3 months ago
- [CVPR 2023] 3D Representation Learning via Foreground Aware Feature Contrast☆40Updated 7 months ago
- Pytorch implementation of the paper Stand-Alone Self-Attention in Vision Models☆23Updated 3 years ago
- BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds - Official PyTorch implementation☆71Updated 5 months ago
- Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).☆54Updated 7 months ago
- GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints☆12Updated 7 months ago
- OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity☆25Updated 3 weeks ago
- [IROS 2024]InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction☆24Updated 4 months ago
- Repository of Trans4PASS (accepted to CVPR2022)☆82Updated last year
- Open-Vocabulary Panoptic Segmentation☆18Updated 2 months ago
- GEDepth: Ground Embedding for Monocular Depth Estimation (ICCV 2023)☆56Updated last year
- Official Repository for "MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection" (ECCV 2024)☆15Updated last month
- Effective unsupervised framework aimed at explicitly addressing confidence estimation of LiDAR sparse depth maps☆21Updated last year