# Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments

arXiv: https://arxiv.org/abs/2207.04526 · HTML: https://mlsanity.com/paper/2207.04526/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 55 references that are in the map.
- First posted on arXiv 10 Jul 2022.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [UPSNet: A Unified Panoptic Segmentation Network](https://mlsanity.com/paper/1901.03784/) (2019)
- [MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning](https://mlsanity.com/paper/2001.06902/) (2020)
- [EfficientPS: Efficient Panoptic Segmentation](https://mlsanity.com/paper/2004.02307/) (2020)

## Built on by (most cited first, 30 of 33)

- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2404.04256/) (2024)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation](https://mlsanity.com/paper/2408.01343/) (2024)
- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation](https://mlsanity.com/paper/2309.14065/) (2023)
- [Efficient Multi-Task Scene Analysis with RGB-D Transformers](https://mlsanity.com/paper/2306.05242/) (2023)
- [PanopticNDT: Efficient and Robust Panoptic Mapping](https://mlsanity.com/paper/2309.13635/) (2023)
- [Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation](https://mlsanity.com/paper/2408.02297/) (2024)
- [OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation](https://mlsanity.com/paper/2509.15096/) (2025)
- [Blocks2World: Controlling Realistic Scenes with Editable Primitives](https://mlsanity.com/paper/2307.03847/) (2023)
- [Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation](https://mlsanity.com/paper/2308.06024/) (2023)
- [ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer](https://mlsanity.com/paper/2307.12349/) (2023)
- [LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks](https://mlsanity.com/paper/2507.22477/) (2025)
- [MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning](https://mlsanity.com/paper/2508.10133/) (2025)
- [M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception](https://mlsanity.com/paper/2510.17363/) (2025)
- [Depth-guided Texture Diffusion for Image Semantic Segmentation](https://mlsanity.com/paper/2408.09097/) (2024)
- [PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes](https://mlsanity.com/paper/2503.18393/) (2025)
- [DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation](https://mlsanity.com/paper/2511.13047/) (2025)
- [A Deep Learning-based Global and Segmentation-based Semantic Feature Fusion Approach for Indoor Scene Classification](https://mlsanity.com/paper/2302.06432/) (2023)
- [Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers](https://mlsanity.com/paper/2601.00359/) (2026)
- [GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth](https://mlsanity.com/paper/2604.11585/) (2026)
- [RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings](https://mlsanity.com/paper/2605.10706/) (2026)
- [Optimizing rgb-d semantic segmentation through multi-modal interaction and pooling attention](https://mlsanity.com/paper/2311.11312/) (2023)
- [Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification](https://mlsanity.com/paper/2404.07739/) (2024)
- [Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2405.10947/) (2024)
- [AMMNet: An Asymmetric Multi-Modal Network for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2507.16158/) (2025)
- [Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues](https://mlsanity.com/paper/2512.07034/) (2025)
- [Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidance](https://mlsanity.com/paper/2603.07570/) (2026)
- [CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation](https://mlsanity.com/paper/2604.02948/) (2026)

## Abstract (arXiv)

Semantic scene understanding is essential for mobile agents acting in various environments. Although semantic segmentation already provides a lot of information, details about individual objects as well as the general scene are missing but required for many real-world applications. However, solving multiple tasks separately is expensive and cannot be accomplished in real time given limited computing and battery capabilities on a mobile platform. In this paper, we propose an efficient multi-task approach for RGB-D scene analysis~(EMSANet) that simultaneously performs semantic and instance segmentation~(panoptic segmentation), instance orientation estimation, and scene classification. We show that all tasks can be accomplished using a single neural network in real time on a mobile platform without diminishing performance - by contrast, the individual tasks are able to benefit from each other. In order to evaluate our multi-task approach, we extend the annotations of the common RGB-D indoor datasets NYUv2 and SUNRGB-D for instance segmentation and orientation estimation. To the best of our knowledge, we are the first to provide results in such a comprehensive multi-task setting for indoor scene analysis on NYUv2 and SUNRGB-D.