# 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation

arXiv: https://arxiv.org/abs/1803.10409 · HTML: https://mlsanity.com/paper/1803.10409/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2018.

## Built on by (most cited first, 30 of 118)

- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [OctFormer: Octree-based Transformers for 3D Point Clouds](https://mlsanity.com/paper/2305.03045/) (2023)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP](https://mlsanity.com/paper/2303.04748/) (2023)
- [Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training](https://mlsanity.com/paper/2308.09718/) (2023)
- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [Panoptic 3D Scene Reconstruction From a Single RGB Image](https://mlsanity.com/paper/2111.02444/) (2021)
- [X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning](https://mlsanity.com/paper/2203.00843/) (2022)
- [UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding](https://mlsanity.com/paper/2212.00836/) (2022)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [OmniSat: Self-Supervised Modality Fusion for Earth Observation](https://mlsanity.com/paper/2404.08351/) (2024)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding](https://mlsanity.com/paper/2112.02990/) (2021)
- [STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset](https://mlsanity.com/paper/2203.09065/) (2022)

## Abstract (arXiv)

We present 3DMV, a novel method for 3D semantic scene segmentation of RGB-D scans in indoor environments using a joint 3D-multi-view prediction network. In contrast to existing methods that either use geometry or RGB data as input for this task, we combine both data modalities in a joint, end-to-end network architecture. Rather than simply projecting color data into a volumetric grid and operating solely in 3D -- which would result in insufficient detail -- we first extract feature maps from associated RGB images. These features are then mapped into the volumetric feature grid of a 3D network using a differentiable backprojection layer. Since our target is 3D scanning scenarios with possibly many frames, we use a multi-view pooling approach in order to handle a varying number of RGB input views. This learned combination of RGB and geometric features with our joint 2D-3D architecture achieves significantly better results than existing baselines. For instance, our final result on the ScanNet 3D segmentation benchmark increases from 52.8% to 75% accuracy compared to existing volumetric architectures.