ImVoxelGNet: Image to voxels geometry-aware projection for multi-view RGB-based 3D object detection
Gang Xu, Biao Leng, Zhang Xiong
TL;DR
ImVoxelGNet improves 3D object detection by better capturing geometric relationships from multiple image views.
Contribution
A novel framework that enhances geometric perception by integrating pixel features more effectively during voxel projection.
Findings
ImVoxelGNet improves 3D object detection performance by 2.2% in mean average precision on the ScanNetV2 dataset.
The framework's integration of pixel features leads to more accurate spatial geometric learning.
An implicit geometric perception structure refines spatial features and improves occupancy relationships in voxels.
Abstract
3D object detection based solely on image data presents a significant challenge in computer vision, primarily due to the need to integrate geometric perception processes derived from visual inputs. The key to overcoming this challenge lies in effectively capturing the geometric relationships across multiple viewpoints, thereby establishing strong geometric priors. Current methods commonly back-project voxels onto images to align voxel-pixel features, yet during this process, pixel features are insufficiently involved in learning, leading to a decrease in geometric perception accuracy and, consequently, impacting detection performance. To address this limitation, we propose a novel network framework called ImVoxelGNet. This framework first integrates features projected onto pixels via a expansion operation, compensating for the pixel information inadequately utilized in traditional…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23
Figure 24
Figure 25
Figure 26
Figure 27
Figure 28
Figure 29
Figure 30
Figure 31
Figure 32
Figure 33
Figure 34
Figure 35
Figure 36
Figure 37
Figure 38
Figure 39
Figure 40
Figure 41
Figure 42
Figure 43Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Robotics and Sensor-Based Localization · 3D Shape Modeling and Analysis