# Bidirectional Projection Network for Cross Dimension Scene Understanding

arXiv: https://arxiv.org/abs/2103.14326 · HTML: https://mlsanity.com/paper/2103.14326/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 72 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](https://mlsanity.com/paper/1704.08545/) (2017)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)

## Built on by (most cited first, 30 of 95)

- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://mlsanity.com/paper/2205.02836/) (2022)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [SAMPart3D: Segment Any Part in 3D Objects](https://mlsanity.com/paper/2411.07184/) (2024)
- [X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning](https://mlsanity.com/paper/2203.00843/) (2022)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2401.07745/) (2024)
- [4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding](https://mlsanity.com/paper/2112.02990/) (2021)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [PointConvFormer: Revenge of the Point-based Convolution](https://mlsanity.com/paper/2208.02879/) (2022)
- [PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection](https://mlsanity.com/paper/2412.12617/) (2024)
- [Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization](https://mlsanity.com/paper/2207.11209/) (2022)
- [ODIN: A Single Model for 2D and 3D Segmentation](https://mlsanity.com/paper/2401.02416/) (2024)
- [Open-World Semantic Segmentation Including Class Similarity](https://mlsanity.com/paper/2403.07532/) (2024)
- [Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding](https://mlsanity.com/paper/2111.15363/) (2021)
- [VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling](https://mlsanity.com/paper/2210.11472/) (2022)
- [Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.11166/) (2023)
- [3DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognition](https://mlsanity.com/paper/2310.18511/) (2023)
- [Point Scene Understanding via Disentangled Instance Mesh Reconstruction](https://mlsanity.com/paper/2203.16832/) (2022)
- [Region-Based Representations Revisited](https://mlsanity.com/paper/2402.02352/) (2024)
- [Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation](https://mlsanity.com/paper/2407.13362/) (2024)
- [2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision](https://mlsanity.com/paper/2310.12817/) (2023)
- [KPConvX: Modernizing Kernel Point Convolution with Kernel Attention](https://mlsanity.com/paper/2405.13194/) (2024)
- [Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2407.09781/) (2024)
- [PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration](https://mlsanity.com/paper/2308.04782/) (2023)
- [FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs](https://mlsanity.com/paper/2403.13507/) (2024)

## Abstract (arXiv)

2D image representations are in regular grids and can be processed efficiently, whereas 3D point clouds are unordered and scattered in 3D space. The information inside these two visual domains is well complementary, e.g., 2D images have fine-grained texture while 3D point clouds contain plentiful geometry information. However, most current visual recognition systems process them individually. In this paper, we present a bidirectional projection network (BPNet) for joint 2D and 3D reasoning in an end-to-end manner. It contains 2D and 3D sub-networks with symmetric architectures, that are connected by our proposed bidirectional projection module (BPM). Via the BPM, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition. Extensive quantitative and qualitative experimental evaluations show that joint reasoning over 2D and 3D visual domains can benefit both 2D and 3D scene understanding simultaneously. Our BPNet achieves top performance on the ScanNetV2 benchmark for both 2D and 3D semantic segmentation. Code is available at urlhttps://github.com/wbhu/BPNet.