Related papers: 3D Orientation Field Transform
For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D…
Light field (LF) imaging captures both angular and spatial light distributions, enabling advanced photographic techniques. However, micro-lens array (MLA)- based cameras face a spatial-angular resolution tradeoff due to a single shared…
We address the problem of generating a 360-degree image from a single image with a narrow field of view by estimating its surroundings. Previous methods suffered from overfitting to the training resolution and deterministic generation. This…
Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…
We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level…
This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields, enabling the first feed-forward model for open-world convex decomposition. Our method produces high-quality…
Estimating and rectifying the orientation angle of any image is a pretty challenging task. Initial work used the hand engineering features for this purpose, where after the invention of deep learning using convolution-based neural network…
As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and…
The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and…
2D object proposals, quickly detected regions in an image that likely contain an object of interest, are an effective approach for improving the computational efficiency and accuracy of object detection in color images. In this work, we…
Research on monocular 3D object detection is being actively studied, and as a result, performance has been steadily improving. However, 3D object detection performance is significantly reduced when applied to a camera system different from…
High-dimensional quantum systems offer many advantages over low-dimensional quantum systems. Meanwhile, unitary transformations on quantum states are important parts in various quantum information tasks, whereas they become technically…
We present a customized 3D mesh Transformer model for the pose transfer task. As the 3D pose transfer essentially is a deformation procedure dependent on the given meshes, the intuition of this work is to perceive the geometric…
Estimating accurate lane lines in 3D space remains challenging due to their sparse and slim nature. Previous works mainly focused on using images for 3D lane detection, leading to inherent projection error and loss of geometry information.…
Remote focusing is widely used in 3D two-photon microscopy and 3D photostimulation because it enables fast axial scanning without moving the objective lens or specimen. However, due to the design constraints of microscope optics, remote…
3D lane detection is an integral part of autonomous driving systems. Previous CNN and Transformer-based methods usually first generate a bird's-eye-view (BEV) feature map from the front view image, and then use a sub-network with BEV…
Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, retrieval, and…
Accurate registration of 2D imagery with point clouds is a key technology for image-LiDAR point cloud fusion, camera to laser scanner calibration and camera localization. Despite continuous improvements, automatic registration of 2D and 3D…
Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned due to differences in 3D camera poses and object shapes. To tackle these issues, we…
We introduce a technique for recovering a sufficiently smooth function from its ray transform over a wide class of curves in a general region of Euclidean space. The method is based on a complexification of the underlying vector fields…