# Generative Sparse Detection Networks for 3D Single-shot Object Detection

arXiv: https://arxiv.org/abs/2006.12356 · HTML: https://mlsanity.com/paper/2006.12356/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 30 of 69)

- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [Multimodal Token Fusion for Vision Transformers](https://mlsanity.com/paper/2204.08721/) (2022)
- [VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids](https://mlsanity.com/paper/2206.07695/) (2022)
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2304.06906/) (2023)
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://mlsanity.com/paper/2112.00322/) (2021)
- [CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds](https://mlsanity.com/paper/2210.04264/) (2022)
- [PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection](https://mlsanity.com/paper/2303.08129/) (2023)
- [Graspness Discovery in Clutters for Fast and Accurate Grasp Detection](https://mlsanity.com/paper/2406.11142/) (2024)
- [NeRF-RPN: A general framework for object detection in NeRFs](https://mlsanity.com/paper/2211.11646/) (2022)
- [Mask-Attention-Free Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2309.01692/) (2023)
- [L3DG: Latent 3D Gaussian Diffusion](https://mlsanity.com/paper/2410.13530/) (2024)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)
- [TR3D: Towards Real-Time Indoor 3D Object Detection](https://mlsanity.com/paper/2302.02858/) (2023)
- [PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection](https://mlsanity.com/paper/2412.12617/) (2024)
- [Uni3DETR: Unified 3D Detection Transformer](https://mlsanity.com/paper/2310.05699/) (2023)
- [PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds](https://mlsanity.com/paper/2109.05566/) (2021)
- [Bridged Transformer for Vision and Point Cloud 3D Object Detection](https://mlsanity.com/paper/2210.01391/) (2022)
- [UniDet3D: Multi-dataset Indoor 3D Object Detection](https://mlsanity.com/paper/2409.04234/) (2024)
- [PeRFception: Perception using Radiance Fields](https://mlsanity.com/paper/2208.11537/) (2022)
- [TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding](https://mlsanity.com/paper/2502.10392/) (2025)
- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2409.18092/) (2024)
- [Deep Point Cloud Reconstruction](https://mlsanity.com/paper/2111.11704/) (2021)
- [Image2Lego: Customized LEGO Set Generation from Images](https://mlsanity.com/paper/2108.08477/) (2021)
- [ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection](https://mlsanity.com/paper/2308.09098/) (2023)
- [Neural Scene Representation for Locomotion on Structured Terrain](https://mlsanity.com/paper/2206.08077/) (2022)
- [Boosting 3D Object Detection via Object-Focused Image Fusion](https://mlsanity.com/paper/2207.10589/) (2022)

## Abstract (arXiv)

3D object detection has been widely studied due to its potential applicability to many promising areas such as robotics and augmented reality. Yet, the sparse nature of the 3D data poses unique challenges to this task. Most notably, the observable surface of the 3D point clouds is disjoint from the center of the instance to ground the bounding box prediction on. To this end, we propose Generative Sparse Detection Network (GSDN), a fully-convolutional single-shot sparse detection network that efficiently generates the support for object proposals. The key component of our model is a generative sparse tensor decoder, which uses a series of transposed convolutions and pruning layers to expand the support of sparse tensors while discarding unlikely object centers to maintain minimal runtime and memory footprint. GSDN can process unprecedentedly large-scale inputs with a single fully-convolutional feed-forward pass, thus does not require the heuristic post-processing stage that stitches results from sliding windows as other previous methods have. We validate our approach on three 3D indoor datasets including the large-scale 3D indoor reconstruction dataset where our method outperforms the state-of-the-art methods by a relative improvement of 7.14% while being 3.78 times faster than the best prior work.