Related papers: PVT-SSD: Single-Stage 3D Object Detector with Poin…

We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature…

Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…

Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…

Image-based 3D object detection aims to identify and localize objects in 3D space using only RGB images, eliminating the need for expensive depth sensors required by point cloud-based methods. Existing image-based approaches face two…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored…

We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively…

While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due to the limitation of Transformers: a demanding need for…

3D object detection based on LiDAR point clouds is a crucial module in autonomous driving particularly for long range sensing. Most of the research is focused on achieving higher accuracy and these models are not optimized for deployment on…

In autonomous driving, accurate 3D lane detection using monocular cameras is important for downstream tasks. Recent CNN and Transformer approaches usually apply a two-stage model design. The first stage transforms the image feature from a…

We propose a novel solution for the task of video panoptic segmentation, that simultaneously predicts pixel-level semantic and instance segmentation and generates clip-level instance tracks. Our network, named VPS-Transformer, with a hybrid…

This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a…

Small objects detection is a challenging task in computer vision due to its limited resolution and information. In order to solve this problem, the majority of existing methods sacrifice speed for improvement in accuracy. In this paper, we…

Recent work on 3D object detection advocates point cloud voxelization in birds-eye view, where objects preserve their physical dimensions and are naturally separable. When represented in this view, however, point clouds are sparse and have…

In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not…

Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet…

Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context.…

Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D…

The multi-line LiDAR is widely used in autonomous vehicles, so point cloud-based 3D detectors are essential for autonomous driving. Extracting rich multi-scale features is crucial for point cloud-based 3D detectors in autonomous driving due…