Related papers: HoHoNet: 360 Indoor Holistic Understanding with La…
The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic.…
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as…
We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall,…
Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…
Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results as the compression process often muddles the semantics between various planes. Besides, these…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
MobileNets, a class of top-performing convolutional neural network architectures in terms of accuracy and efficiency trade-off, are increasingly used in many resourceaware vision applications. In this paper, we present Harmonious Bottleneck…
Human head pose estimation in images has applications in many fields such as human-computer interaction or video surveillance tasks. In this work, we address this problem, defined here as the estimation of both vertical (tilt/pitch) and…
Recent advances in high-definition (HD) map construction from surround-view images have highlighted their cost-effectiveness in deployment. However, prevailing techniques often fall short in accurately extracting and utilizing road…
Since Convolutional Neural Networks (ConvNets) are able to simultaneously learn features and classifiers to discriminate different categories of activities, recent works have employed ConvNets approaches to perform human activity…
This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…
Indoor 360 panoramas have two essential properties. (1) The panoramas are continuous and seamless in the horizontal direction. (2) Gravity plays an important role in indoor environment design. By leveraging these properties, we present…
Depth completion endeavors to reconstruct a dense depth map from sparse depth measurements, leveraging the information provided by a corresponding color image. Existing approaches mostly hinge on single-scale propagation strategies that…
High resolution and advanced semantic representation are both vital for dense prediction. Empirically, low-resolution feature maps often achieve stronger semantic representation, and high-resolution feature maps generally can better…
Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still not well-handled. To alleviate these…
Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines,…
We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to…
The rise of Transformer architectures has advanced medical image segmentation, leading to hybrid models that combine Convolutional Neural Networks (CNNs) and Transformers. However, these models often suffer from excessive complexity and…
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these…
The remote sensing image change detection task is an essential method for large-scale monitoring. We propose HSANet, a network that uses hierarchical convolution to extract multi-scale features. It incorporates hybrid self-attention and…