Papers › Frustum VoxNet for 3D object detection from RGB-D or Depth images

Frustum VoxNet for 3D object detection from RGB-D or Depth images

12 Oct 2019arXiv:1910.05483archive 2025-07-28

Xiaoke Shen, Ioannis Stamos

Recently, there have been a plethora of classification and detection systems from RGB as well as 3D images. In this work, we describe a new 3D object detection system from an RGB-D or depth-only point cloud. Our system first detects objects in 2D (either RGB or pseudo-RGB constructed from depth). The next step is to detect 3D objects within the 3D frustums these 2D detections define. This is achieved by voxelizing parts of the frustums (since frustums can be really large), instead of using the whole frustums as done in earlier work. The main novelty of our system has to do with determining which parts (3D proposals) of the frustums to voxelize, thus allowing us to provide high resolution representations around the objects of interest. It also allows our system to have reduced memory requirements. These 3D proposals are fed to an efficient ResNet-based 3D Fully Convolutional Network (FCN). Our 3D detection system is fast and can be integrated into a robotics platform. With respect to systems that do not perform voxelization (such as PointNet), our methods can operate without the requirement of subsampling of the datasets. We have also introduced a pipelining approach that further improves the efficiency of our system. Results on SUN RGB-D dataset show that our system, which is based on a small network, can process 20 frames per second with comparable detection results to the state-of-the-art, achieving a 2 times speedup.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Object DetectionObject DetectionObject Detection In Indoor Scenes

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection SUN-RGBD val Frustum VoxNet (+3D ResNetFCN6) Inference Speed (s) 0.16 #30 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val Frustum VoxNet (+3D ResNetFCN6) mAP@0.25 37.7 #30 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val Frustum VoxNet (YOLO v3+3D ResNetFCN6) Inference Speed (s) 0.048 #31 of 32 Archive leaderboard report
Object Detection In Indoor Scenes SUN RGB-D Frustum VoxNet (RGB) AP 0.5 47.9 #5 of 7 Archive leaderboard report
Object Detection In Indoor Scenes SUN RGB-D Frustum VoxNet (Depth only) AP 0.5 42.8 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections