Related papers: FSD-BEV: Foreground Self-Distillation for Multi-vi…

Recently, perception task based on Bird's-Eye View (BEV) representation has drawn more and more attention, and BEV representation is promising as the foundation for next-generation Autonomous Vehicle (AV) perception. However, most existing…

Contrastive image-to-LiDAR knowledge transfer, commonly used for learning 3D representations with synchronized images and point clouds, often faces a self-conflict dilemma. This issue arises as contrastive losses unintentionally dissociate…

Although multiview fusion has demonstrated potential in LiDAR segmentation, its dependence on computationally intensive point-based interactions, arising from the lack of fixed correspondences between views such as range view and Bird's-Eye…

Accurate 3D object detection in autonomous driving is critical yet challenging due to occlusions, varying object sizes, and complex urban environments. This paper introduces the KAN-RCBEVDepth method, an innovative approach aimed at…

Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds.…

In incremental object detection, knowledge distillation has been proven to be an effective way to alleviate catastrophic forgetting. However, previous works focused on preserving the knowledge of old models, ignoring that images could…

Bird's eye view (BEV) semantic segmentation plays a crucial role in spatial sensing for autonomous driving. Although recent literature has made significant progress on BEV map understanding, they are all based on single-agent camera-based…

Frame-wise semantic segmentation of indoor lidar scans is a fundamental step toward higher-level 3D scene understanding and mapping applications. However, acquiring frame-wise ground truth for training deep learning models is costly and…

Fully Unsupervised Anomaly Detection (FUAD) is a practical extension of Unsupervised Anomaly Detection (UAD), aiming to detect anomalies without any labels even when the training set may contain anomalous samples. To achieve FUAD, we…

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

Vision-centric bird-eye-view (BEV) perception has shown promising potential in autonomous driving. Recent works mainly focus on improving efficiency or accuracy but neglect the challenges when facing environment changing, resulting in…

Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high…

Camera-based Bird's-Eye-View (BEV) perception often struggles between adopting 3D-to-2D or 2D-to-3D view transformation (VT). The 3D-to-2D VT typically employs resource-intensive Transformer to establish robust correspondences between 3D…

Comprehending the environment and accurately detecting objects in 3D space are essential for advancing autonomous vehicle technologies. Integrating Camera and LIDAR data has emerged as an effective approach for achieving high accuracy in 3D…

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…

With the rapid development of computer vision, Vision Transformers (ViTs) offer the tantalising prospect of unified information processing across visual and textual domains due to the lack of inherent inductive biases in ViTs. ViTs require…

In this paper, we propose the first self-distillation framework for general object detection, termed LGD (Label-Guided self-Distillation). Previous studies rely on a strong pretrained teacher to provide instructive knowledge that could be…

Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its…

Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…

In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs. The conventional feature imitation…