Related papers: Rotation Transformation Network: Learning View-Inv…
The design of a tiny machine learning model, which can be deployed in mobile and edge devices, for point cloud object classification is investigated in this work. To achieve this objective, we replace the multi-scale representation of a…
Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored.…
Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments. In…
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…
3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature…
We propose a novel framework for training neural networks which is capable of learning 3D information of non-rigid objects when only 2D annotations are available as ground truths. Recently, there have been some approaches that incorporate…
Deep neural networks (DNN) have been widely used and play a major role in the field of computer vision and autonomous navigation. However, these DNNs are computationally complex and their deployment over resource-constrained platforms is…
Spatial and channel re-calibration have become powerful concepts in computer vision. Their ability to capture long-range dependencies is especially useful for those networks that extract local features, such as CNNs. While re-calibration…
In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for…
Point clouds and RGB images are naturally complementary modalities for 3D visual understanding - the former provides sparse but accurate locations of points on objects, while the latter contains dense color and texture information. Despite…
Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Unlike classical optimization-based methods, recent learning-based methods leverage the power of deep learning for…
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in…
High-resolution remote sensing imagery increasingly contains dense clusters of tiny objects, the detection of which is extremely challenging due to severe mutual occlusion and limited pixel footprints. Existing detection methods typically…
Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface…
Implicit function based surface reconstruction has been studied for a long time to recover 3D shapes from point clouds sampled from surfaces. Recently, Signed Distance Functions (SDFs) and Occupany Functions are adopted in learning-based…
Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct…
Point clouds are a widely available and canonical data modality which convey the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains…
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases…
The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as…
Decision Transformer (DT), a trajectory modelling method, has shown competitive performance compared to traditional offline reinforcement learning (RL) approaches on various classic control tasks. However, it struggles to learn optimal…