Dynamic token selection and training only 1.6 million parameters instead of over 300 million reduces computation by 48-55% and improves accuracy over prior state-of-the-art on the NuScenes dataset.
Time will tell: New out- looks and a baseline for temporal multi-view 3d object detection
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
fields
cs.CV 6representative citing papers
CLLAP generates LiDAR-based pseudo-radar data and applies dual-modality contrastive pretraining to boost radar-camera fusion models for 3D detection, showing gains on NuScenes and Lyft datasets.
CAM3DNet outperforms prior camera-based 3D detectors on nuScenes, Waymo and Argoverse by using three new modules to better mine multi-scale spatiotemporal features from 2D queries and pyramid maps.
RQR3D reparametrizes oriented bounding box regression in BEV 3D detection as regressing a horizontal box plus corner offsets and achieves SOTA camera-radar performance on nuScenes with 67.5 NDS and 59.7 mAP.
LAW introduces a self-supervised prediction task on latent scene features that boosts end-to-end driving performance on nuScenes, NAVSIM, and CARLA benchmarks.
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.
citing papers explorer
-
Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning
Dynamic token selection and training only 1.6 million parameters instead of over 300 million reduces computation by 48-55% and improves accuracy over prior state-of-the-art on the NuScenes dataset.
-
CLLAP: Contrastive Learning-based LiDAR-Augmented Pretraining for Enhanced Radar-Camera Fusion
CLLAP generates LiDAR-based pseudo-radar data and applies dual-modality contrastive pretraining to boost radar-camera fusion models for 3D detection, showing gains on NuScenes and Lyft datasets.
-
CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras
CAM3DNet outperforms prior camera-based 3D detectors on nuScenes, Waymo and Argoverse by using three new modules to better mine multi-scale spatiotemporal features from 2D queries and pyramid maps.
-
RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection
RQR3D reparametrizes oriented bounding box regression in BEV 3D detection as regressing a horizontal box plus corner offsets and achieves SOTA camera-radar performance on nuScenes with 67.5 NDS and 59.7 mAP.
-
Enhancing End-to-End Autonomous Driving with Latent World Model
LAW introduces a self-supervised prediction task on latent scene features that boosts end-to-end driving performance on nuScenes, NAVSIM, and CARLA benchmarks.
-
SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.