EnVision-Research / SyntheOcc
☆24Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for SyntheOcc
- [WACV'25] Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding☆44Updated 7 months ago
- ☆20Updated 7 months ago
- [ECCV 2024] Official implementation for "RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception"☆20Updated 3 months ago
- WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation☆78Updated last month
- [ECCV 2024] 4D Contrastive Superflows are Dense 3D Representation Learners☆40Updated last month
- [ECCV 2024] ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers☆36Updated last week
- [CVPR 2023] MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training☆46Updated last year
- [IROS 2024]InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction☆23Updated 4 months ago
- Official PyTorch Implementation of HTCL (ECCV 2024): Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion☆33Updated 4 months ago
- [ECCV 2024] Occupancy as Set of Points☆81Updated 4 months ago
- ☆24Updated 2 months ago
- ☆52Updated 11 months ago
- Multi-Space Alignments Towards Universal LiDAR Segmentation☆39Updated 2 weeks ago
- DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection☆35Updated last year
- [ECCV 2024] Official implementation of "RangeLDM: Fast Realistic LiDAR Point Cloud Generation"☆16Updated last month
- [NeurIPS 2024] DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model☆23Updated last week
- Project Page for GaussianFormer☆22Updated 5 months ago
- Implementation of "PG-RCNN: Semantic Surface Point Generation for 3D Object Detection" (ICCV 2023)☆30Updated 8 months ago
- Official Code Release of Delphi☆51Updated 5 months ago
- ☆42Updated 3 months ago
- ☆52Updated 6 months ago
- Official implementation for the ICCV 2023 paper "NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates…☆33Updated 11 months ago
- DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes☆40Updated last week
- Official code implementation for the paper "X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios"☆14Updated last week
- [ECCV 2024] Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression☆37Updated last month
- ☆74Updated last year
- MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning☆62Updated 7 months ago
- (ICCV2023) MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection☆80Updated 10 months ago
- DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction☆16Updated last month