# Memory-based Adapters for Online 3D Scene Perception

arXiv: https://arxiv.org/abs/2403.06974 · HTML: https://mlsanity.com/paper/2403.06974/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 49 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning](https://mlsanity.com/paper/2201.10029/) (2022)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [MoViNets: Mobile Video Networks for Efficient Video Recognition](https://mlsanity.com/paper/2103.11511/) (2021)
- [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things](https://mlsanity.com/paper/1903.01177/) (2019)
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://mlsanity.com/paper/2112.00322/) (2021)
- [Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1609.06666/) (2016)

## Built on by (most cited first, 13 of 13)

- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding](https://mlsanity.com/paper/2412.04380/) (2024)
- [EmbodiedSAM: Online Segment Any 3D Thing in Real Time](https://mlsanity.com/paper/2408.11811/) (2024)
- [Online Segment Any 3D Thing as Instance Tracking](https://mlsanity.com/paper/2512.07599/) (2025)
- [MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors](https://mlsanity.com/paper/2512.15577/) (2025)
- [BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion](https://mlsanity.com/paper/2506.15610/) (2025)
- [Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance](https://mlsanity.com/paper/2508.15650/) (2025)
- [OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution](https://mlsanity.com/paper/2603.02134/) (2026)
- [Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian Fusion](https://mlsanity.com/paper/2512.06882/) (2025)
- [EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2603.04254/) (2026)
- [ESAM++: Efficient Online 3D Perception on the Edge](https://mlsanity.com/paper/2605.29505/) (2026)
- [4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads](https://mlsanity.com/paper/2510.17664/) (2025)
- [AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks](https://mlsanity.com/paper/2609.38864/) (2026)

## Abstract (arXiv)

In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input, which is not applicable in robotic applications where the input data is streaming RGB-D videos rather than a complete 3D scene reconstructed from pre-collected RGB-D videos. To deal with online 3D scene perception tasks where data collection and perception should be performed simultaneously, the model should be able to process 3D scenes frame by frame and make use of the temporal information. To this end, we propose an adapter-based plug-and-play module for the backbone of 3D scene perception model, which constructs memory to cache and aggregate the extracted RGB-D features to empower offline models with temporal learning ability. Specifically, we propose a queued memory mechanism to cache the supporting point cloud and image features. Then we devise aggregation modules which directly perform on the memory and pass temporal information to current frame. We further propose 3D-to-2D adapter to enhance image features with strong global context. Our adapters can be easily inserted into mainstream offline architectures of different tasks and significantly boost their performance on online tasks. Extensive experiments on ScanNet and SceneNN datasets demonstrate our approach achieves leading performance on three 3D scene perception tasks compared with state-of-the-art online methods by simply finetuning existing offline models, without any model and task-specific designs. hrefhttps://xuxw98.github.io/Online3D/Project page.