MAD: Memory-Augmented Detection of 3D Objects
Ben Agro, Sergio Casas, Patrick Wang, Thomas Gilles, Raquel Urtasun
2025Year
4Top-tier citations
Abstract
Detector (b) Object Memory (c) Memory Augmented Detections 0.0s -2.4s Memory Age False Negative Figure 1. Detectors without long-term temporal fusion (a) miss heavily occluded objects. Our approach enhances detectors (b) to remember past predictions, (c) recovering from occlusion. Detections are in green , labels are in black , lidar points are in • gray.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2fee36fb-3874-49c9-bc38-2f193356c0dbCited by top-tier papers4
- Efficiency Follows Global-Local DecouplingZhenyu Yang, Gensheng Pei, Tao Chen, Yichao Zhou et al.CVPR 2026 · 3 citations
- Scene Reconstruction as Mapping Priors for 3D DetectionYang Fu, Yuliang Zou, Hao Xiang, Xin Huang et al.CVPR 2026 · 1 citation
- OneSparse: A Unified Framework for Sparse Activation Layers in Vision ModelsXingkui Zhu, Dingkang Liang, Cheng Chen, Daoxin Zhang et al.CVPR 2026
- MORE-STEM: Long-Short MemOry REcall and Spatio-TEmporal Consistency Model for Query-Driven 3D/4D Point Cloud SegmentationChade Li, Haida Feng, Pengju Zhang, Yihong WuCVPR 2026
Builds on28
- Revisiting the Calibration of Modern Neural NetworksMatthias Minderer, Josip Djolonga, Rob Romijnders, Frances Hubis et al.NeurIPS 2021 · 633 citations
- PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesYingfei Liu, Junjie Yan, Fan Jia, Shuailin Li et al.ICCV 2023 · 513 citations
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous DrivingYurong You, Yan Wang, Wei-Lun Chao, Divyansh Garg et al.ICLR 2020 · 439 citations
- Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object DetectionShihao Wang, Yingfei Liu, Tiancai Wang, Ying Li et al.ICCV 2023 · 399 citations
- FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasAnthony Hu, Zak Murez, Nikhil Mohan, Sofía Dudas et al.ICCV 2021 · 329 citations
Related papers
- MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud SequencesYingwei Li, Charles R. Qi, Yin Zhou, Chenxi Liu et al.CVPR 2023
- LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object DetectionJin Fang, Xinxin Zuo, Dingfu Zhou, Shengze Jin et al.CVPR 2021
- Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR RepresentationsXiang Xu, Lingdong Kong, Song Wang, Chuanwei Zhou et al.ICCV 2025 · 1 citation
- Multimodal Virtual Point 3D DetectionTianwei Yin, Xingyi Zhou, Philipp KrähenbühlNeurIPS 2021 · 379 citations
- Query-based Temporal Fusion with Explicit Motion for 3D Object DetectionJinghua Hou, Zhe Liu, Dingkang Liang, Zhikang Zou et al.NeurIPS 2023 · 28 citations
