11 accepted papers
We propose GO-N3RDet, a scene-geometry optimized multi-view 3D object detector enhanced by neural radiance fields. The key to accurate 3D object detection is in effective voxel representation. However, due to occlusion and lack of 3D information, constructing 3D features from multi-view 2D images is…
Place recognition is an important technique for autonomous mobile robotic applications. While single-modal sensor-based approaches have shown satisfactory performance, cross-modal place recognition remains underexplored due to the challenge of bridging the cross-modal heterogeneity gap. In this work
Place recognition is a fundamental technology of high relevance for autonomous robot navigation. Existing methods encounter significant challenges arising from scene variations (e.g., illumination changes, dynamic objects), view-point shifts, and difficulties in data fusion and alignment. These fact
The robustness of correspondence-based point cloud registration relies on transformation invariance and intrinsic distinctiveness of the descriptors computed for registration. However, for challenging scenarios with different objects having similar local geometry and low point cloud overlap, existin
Encoder-Decoder structure is a popular choice in point cloud processing for dense multi-classification tasks, e.g., 3D semantic segmentation. Though existing techniques that follow this structure achieve high performance, they are known to suffer from fine-grained information loss, especially when t
Multi-Layer Perceptron (MLP) models are the bedrock of contemporary point cloud processing. However, their complex network architectures obscure the source of their strength. We first develop an “abstraction and refinement” (ABS-REF) view for the neural modeling of point clouds. This view elucidates…
Due to the resource-intensive nature of training vision-language models on expansive video data a majority of studies have centered on adapting pre-trained image-language models to the video domain. Dominant pipelines propose to tackle the visual discrepancies with additional temporal learners while…
Loop closing is a crucial component in SLAM that helps eliminate accumulated errors through two main steps: loop detection and loop pose correction. The first step determines whether loop closing should be performed, while the second estimates the 6-DoF pose to correct odometry drift. Current method
3D object detection techniques commonly follow a pipeline that aggregates predicted object central point features to compute candidate points. However, these candidate points contain only positional information, largely ignoring the object-level shape information. This eventually leads to sub-optima…
Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, con
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate. In this paper, we propose to learn light field saliency from pixel-level noisy labels obta…