Related papers: SphereUFormer: A U-Shaped Transformer for Spherica…
Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often adapt an…
360{\deg} cameras have gained popularity over the last few years. In this paper, we propose two fundamental techniques -- Field-of-View IoU (FoV-IoU) and 360Augmentation for object detection in 360{\deg} images. Although most object…
To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a…
We present in this paper new multiscale transforms on the sphere, namely the isotropic undecimated wavelet transform, the pyramidal wavelet transform, the ridgelet transform and the curvelet transform. All of these transforms can be…
This work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degraded images and use…
Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is…
This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set"…
Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e.g., SwinIR) can significantly improve the model performance. Still, the computation overhead is also considerable when the…
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown…
We present Laneformer, a conceptually simple yet powerful transformer-based architecture tailored for lane detection that is a long-standing research topic for visual perception in autonomous driving. The dominant paradigms rely on purely…
Effectively preserving and encoding structure features from objects in irregular and sparse LiDAR points is a key challenge to 3D object detection on point cloud. Recently, Transformer has demonstrated promising performance on many 2D and…
Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…
Depth estimation from a monocular 360 image is important to the perception of the entire 3D environment. However, the inherent distortion and large field of view (FoV) in 360 images pose great challenges for this task. To this end, existing…
Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. When bounding boxes overlap, most existing methods lack explicit occlusion information,…
Depth in the real world is rarely singular. Transmissive materials create layered ambiguities that confound conventional perception systems. Existing models remain passive; conventional approaches typically estimate static depth maps…
The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing…
Ideally, 360{\deg} imagery could inherit the deep convolutional neural networks (CNNs) already trained with great success on perspective projection images. However, existing methods to transfer CNNs from perspective to spherical images…
In this paper, a multi-modal 360$^{\circ}$ framework for 3D object detection and tracking for autonomous vehicles is presented. The process is divided into four main stages. First, images are fed into a CNN network to obtain instance…
Vision-based Semantic Scene Completion (SSC) has gained much attention due to its widespread applications in various 3D perception tasks. Existing sparse-to-dense approaches typically employ shared context-independent queries across various…
Due to the rapid development of panorama cameras, the task of estimating panorama depth has attracted significant attention from the computer vision community, especially in applications such as robot sensing and autonomous driving.…