Driveworld: 4d pre-trained scene understanding via world models for autonomous driving
Vision-centric autonomous driving has recently raised wide attention due to its lower cost.
Pre-training is essential for extracting a universal representation. However current vision …
Pre-training is essential for extracting a universal representation. However current vision …
RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features
The inherent noisy and sparse characteristics of radar data pose challenges in finding
effective representations for 3D object detection. In this paper we propose RadarDistill a …
effective representations for 3D object detection. In this paper we propose RadarDistill a …
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
S Sirko-Galouchenko, A Boulch… - Proceedings of the …, 2024 - openaccess.thecvf.com
We introduce a self-supervised pretraining method called OccFeat for camera-only Bird's-
Eye-View (BEV) segmentation networks. With OccFeat we pretrain a BEV network via …
Eye-View (BEV) segmentation networks. With OccFeat we pretrain a BEV network via …
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
Monocular 3D detectors achieve remarkable performance on cars and smaller objects.
However their performance drops on larger objects leading to fatal accidents. Some attribute …
However their performance drops on larger objects leading to fatal accidents. Some attribute …
CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation
In the field of 3D object detection for autonomous driving LiDAR-Camera (LC) fusion is the
top-performing sensor configuration. Still LiDAR is relatively high cost which hinders …
top-performing sensor configuration. Still LiDAR is relatively high cost which hinders …
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
Contrastive learning has emerged as a promising paradigm for 3D open-world
understanding ie aligning point cloud representation to image and text embedding space …
understanding ie aligning point cloud representation to image and text embedding space …
Bev-io: Enhancing bird's-eye-view 3d detection with instance occupancy
A popular approach for constructing bird's-eye-view (BEV) representation in 3D detection is
to lift 2D image features onto the viewing frustum space based on explicitly predicted depth …
to lift 2D image features onto the viewing frustum space based on explicitly predicted depth …
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection
Monocular 3D object detection (Mono3D) is an indispensable research topic in autonomous
driving, thanks to the cost-effective monocular camera sensors and its wide range of …
driving, thanks to the cost-effective monocular camera sensors and its wide range of …
Distilling Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection
H Zheng, D Cao, J Xu, R Ai, W Gu, Y Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
Striking a balance between precision and efficiency presents a prominent challenge in the
bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods …
bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods …
[PDF][PDF] EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network
T Wen, M Yang, Y Xu, D Yang - arxiv.org
3D occupancy prediction (Occ) is a rapidly rising challenging perception task in the field of
autonomous driving which represents the driving scene as uniformly partitioned 3D voxel …
autonomous driving which represents the driving scene as uniformly partitioned 3D voxel …