Robust Camera Only 3D Object Detection
11 papers with code • 1 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Robust Camera Only 3D Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
nuScenes-C
Most implemented papers
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
In a nutshell, BEVFormer exploits both spatial and temporal information by interacting with spatial and temporal space through predefined grid-shaped BEV queries.
BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View
As a fast version, BEVDet-Tiny scores 31. 2% mAP and 39. 2% NDS on the nuScenes val set.
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection
megvii-basedetection/bevdepth
•
•
In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird's-Eye-View (BEV) 3D object detection.
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
synsin0/srcn3d
•
•
Our novel sparse feature sampling module only utilizes local 2D region of interest (RoI) features calculated by the projection of 3D query boxes for further box refinement, leading to a fully-convolutional and deployment-friendly pipeline.
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
wangyueft/detr3d
•
•
This top-down approach outperforms its bottom-up counterpart in which object bounding box prediction follows per-pixel depth estimation, since it does not suffer from the compounding error introduced by a depth prediction model.
PETR: Position Embedding Transformation for Multi-View 3D Object Detection
Object query can perceive the 3D position-aware features and perform end-to-end object detection.
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world.
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception.
Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion
Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task.
