Related papers: SPOT-Occ: Sparse Prototype-guided Transformer for …
Obstacle detection and tracking represent a critical component in robot autonomous navigation. In this paper, we propose ODTFormer, a Transformer-based model to address both obstacle detection and tracking problems. For the detection task,…
In this work, we present SpaRC, a novel Sparse fusion transformer for 3D perception that integrates multi-view image semantics with Radar and Camera point features. The fusion of radar and camera modalities has emerged as an efficient…
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite…
Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs)…
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…
Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. However, this space uses a low x, y-resolution and sacrifices…
Semantic segmentation in autonomous driving has been undergoing an evolution from sparse point segmentation to dense voxel segmentation, where the objective is to predict the semantic occupancy of each voxel in the concerned 3D space. The…
3D occupancy and scene flow offer a detailed and dynamic representation of 3D scene. Recognizing the sparsity and complexity of 3D space, previous vision-centric methods have employed implicit learning-based approaches to model spatial and…
3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in…
3D occupancy prediction plays a pivotal role in the realm of autonomous driving, as it provides a comprehensive understanding of the driving environment. Most existing methods construct dense scene representations for occupancy prediction,…
Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…
The performance of multi-modal 3D occupancy prediction is limited by ineffective fusion, mainly due to geometry-semantics mismatch from fixed fusion strategies and surface detail loss caused by sparse, noisy annotations. The mismatch stems…
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space.…
While Vision Transformers (ViT) have demonstrated remarkable performance across diverse tasks, their computational demands are substantial, scaling quadratically with the number of processed tokens. Compact attention representations,…
3D single object tracking is a key task in 3D computer vision. However, the sparsity of point clouds makes it difficult to compute the similarity and locate the object, posing big challenges to the 3D tracker. Previous works tried to solve…
Comprehensive modeling of the surrounding 3D world is key to the success of autonomous driving. However, existing perception tasks like object detection, road structure segmentation, depth & elevation estimation, and open-set object…
Vision-based 3D semantic scene completion (SSC) describes autonomous driving scenes through 3D volume representations. However, the occlusion of invisible voxels by scene surfaces poses challenges to current SSC methods in hallucinating…
Under-Display Camera (UDC) is an emerging technology that achieves full-screen display via hiding the camera under the display panel. However, the current implementation of UDC causes serious degradation. The incident light required for…
The sparse object detection paradigm shift towards dense 3D semantic occupancy prediction is necessary for dealing with long-tail safety challenges for autonomous vehicles. Nonetheless, the current voxelization methods commonly suffer from…