# DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

arXiv: https://arxiv.org/abs/2304.13031 · HTML: https://mlsanity.com/paper/2304.13031/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 67 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 30 of 50)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Vector Neurons: A General Framework for SO(3)-Equivariant Networks](https://mlsanity.com/paper/2104.12229/) (2021)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2111.12903/) (2021)
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://mlsanity.com/paper/2112.00322/) (2021)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2012.04355/) (2020)
- [Densely Guided Knowledge Distillation using Multiple Teacher Assistants](https://mlsanity.com/paper/2009.08825/) (2020)
- [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1808.02201/) (2018)
- [Generative Sparse Detection Networks for 3D Single-shot Object Detection](https://mlsanity.com/paper/2006.12356/) (2020)
- [Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors](https://mlsanity.com/paper/2206.09500/) (2022)
- [Physically-Based Editing of Indoor Scene Lighting from a Single Image](https://mlsanity.com/paper/2205.09343/) (2022)
- [CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds](https://mlsanity.com/paper/2210.04264/) (2022)
- [Semi-supervised Semantic Segmentation with Error Localization Network](https://mlsanity.com/paper/2204.02078/) (2022)
- [UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2205.10334/) (2022)

## Built on by (most cited first, 16 of 16)

- [P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors](https://mlsanity.com/paper/2403.10521/) (2024)
- [Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving](https://mlsanity.com/paper/2409.06702/) (2024)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [FastMAC: Stochastic Spectral Sampling of Correspondence Graph](https://mlsanity.com/paper/2403.08770/) (2024)
- [FairDiff: Fair Segmentation with Point-Image Diffusion](https://mlsanity.com/paper/2407.06250/) (2024)
- [Training-Free Model Merging for Multi-target Domain Adaptation](https://mlsanity.com/paper/2407.13771/) (2024)
- [PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments](https://mlsanity.com/paper/2404.03634/) (2024)
- [Weakly Supervised Monocular 3D Detection with a Single-View Image](https://mlsanity.com/paper/2402.19144/) (2024)
- [SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis](https://mlsanity.com/paper/2403.09638/) (2024)
- [V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations](https://mlsanity.com/paper/2412.11412/) (2024)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [Bayesian Self-Training for Semi-Supervised 3D Segmentation](https://mlsanity.com/paper/2409.08102/) (2024)
- [DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning](https://mlsanity.com/paper/2411.08340/) (2024)
- [HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target Scoring](https://mlsanity.com/paper/2505.23129/) (2025)
- [Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labels](https://mlsanity.com/paper/2312.06799/) (2023)
- [Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection](https://mlsanity.com/paper/2501.15449/) (2025)

## Abstract (arXiv)

In this paper, we study the problem of semi-supervised 3D object detection, which is of great importance considering the high annotation cost for cluttered 3D indoor scenes. We resort to the robust and principled framework of selfteaching, which has triggered notable progress for semisupervised learning recently. While this paradigm is natural for image-level or pixel-level prediction, adapting it to the detection problem is challenged by the issue of proposal matching. Prior methods are based upon two-stage pipelines, matching heuristically selected proposals generated in the first stage and resulting in spatially sparse training signals. In contrast, we propose the first semisupervised 3D detection algorithm that works in the singlestage manner and allows spatially dense training signals. A fundamental issue of this new design is the quantization error caused by point-to-voxel discretization, which inevitably leads to misalignment between two transformed views in the voxel domain. To this end, we derive and implement closed-form rules that compensate this misalignment onthe-fly. Our results are significant, e.g., promoting ScanNet mAP@0.5 from 35.2% to 48.5% using 20% annotation. Codes and data will be publicly available.