Domain shifts such as sensor type changes and geographical situation variations are
prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on …

Abstract Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled
text-image pairs, has demonstrated great performance in open-world vision understanding …

Closed-set 3D perception models trained on only a pre-defined set of object categories can
be inadequate for safety critical applications such as autonomous driving where new object …

Training a 3D scene understanding model requires complicated human annotations, which
are laborious to collect and result in a model only encoding close-set object semantics. In …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Large-scale pre-trained models have shown promising open-world performance for both
vision and language tasks. However, their transferred capacity on 3D point clouds is still …

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training
(CLIP) have shown inspirational performance on 2D visual recognition, which learns to …

Open-vocabulary scene understanding aims to localize and recognize unseen categories
beyond the annotated label space. The recent breakthrough of 2D open-vocabulary …

Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great
significance to autonomous driving. Most existing 3D reconstruction methods cannot be …

Recent advancements in multimodal pre-training have shown promising efficacy in 3D
representation learning by aligning multimodal features across 3D shapes their 2D …