Related papers: HGL: Hierarchical Geometry Learning for Test-time …

Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the…

Understanding point clouds captured from the real-world is challenging due to shifts in data distribution caused by varying object scales, sensor angles, and self-occlusion. Prior works have addressed this issue by combining recent learning…

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross…

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…

Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…

Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. However, in scenes with repetitive patterns, images often lack…

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between…

Efficient analysis of point clouds holds paramount significance in real-world 3D applications. Currently, prevailing point-based models adhere to the PointNet++ methodology, which involves embedding and abstracting point features within a…

Deep learning models often struggle with generalization when deploying on real-world data, due to the common distributional shift to the training data. Test-time adaptation (TTA) is an emerging scheme used at inference time to address this…

Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by…

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to…

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally…

Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed in real-world scenarios often suffer from performance degradation due to continuous domain…

We tackle the problem of localizing 3D point cloud submaps using complex and diverse natural language descriptions, and present Text2Loc++, a novel neural network designed for effective cross-modal alignment between language and point…

Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it challenging to achieve effective and…

Learning meaningful local and global information remains a challenge in point cloud segmentation tasks. When utilizing local information, prior studies indiscriminately aggregates neighbor information from different classes to update query…

Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and point clouds makes it challenging to learn features that are…

Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis. However, these methods often suffer from suboptimal graph structures, particularly due to sparse connections at boundary…

Test-Time Adaptation (TTA) offers a practical solution for deploying image segmentation models under domain shift without accessing source data or retraining. Among existing TTA strategies, pseudo-label-based methods have shown promising…