SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining

• URL: http://arxiv.org/abs/2503.19912v1
• Date: Tue, 25 Mar 2025 17:59:57 GMT
• Title: SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining
• Authors: Xiang Xu, Lingdong Kong, Hui Shuai, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu, Qingshan Liu,
• Abstract summary: SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs.<n>We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions.<n>With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
• Score: 62.433137130087445
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera sensors, they often overlook the temporal dynamics critical for capturing motion and scene continuity in driving scenarios. To address this limitation, we propose SuperFlow++, a novel framework that integrates spatiotemporal cues in both pretraining and downstream tasks using consecutive LiDAR-camera pairs. SuperFlow++ introduces four key components: (1) a view consistency alignment module to unify semantic information across camera views, (2) a dense-to-sparse consistency regularization mechanism to enhance feature robustness across varying point cloud densities, (3) a flow-based contrastive learning approach that models temporal relationships for improved scene understanding, and (4) a temporal voting strategy that propagates semantic information across LiDAR scans to improve prediction consistency. Extensive evaluations on 11 heterogeneous LiDAR datasets demonstrate that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions. Furthermore, by scaling both 2D and 3D backbones during pretraining, we uncover emergent properties that provide deeper insights into developing scalable 3D foundation models. With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving. The code is publicly available at https://github.com/Xiangxu-0103/SuperFlow

Related papers

• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [52.83707400688378]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets. Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples. Our approach delivers significant performance improvements over state-of-the-art methods in both linear probing and fine-tuning tasks for both LiDAR-based segmentation and object detection.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction [89.89610257714006]
  Existing methods prioritize higher accuracy to cater to the demands of these tasks. We introduce a series of targeted improvements for 3D semantic occupancy prediction and flow estimation. Our purelytemporalal architecture framework, named ALOcc, achieves an optimal tradeoff between speed and accuracy.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
  We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
  arXiv  Detail & Related papers  (2024-07-08T17:59:54Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving [18.88208422580103]
  Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. Current state-of-the-art methods require annotated data to train scene flow networks. We propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline.
  arXiv  Detail & Related papers  (2024-07-01T18:22:54Z)
• STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow [5.476991379461233]
  We propose global attentive flow embedding to match all-to-all point pairs in both Euclidean space. We leverage novel domain adaptive losses to bridge the gap of motion inference from synthetic to real-world. Our approach achieves state-of-the-art performance across various datasets, with particularly outstanding results on real-world LiDAR-scanned datasets.
  arXiv  Detail & Related papers  (2024-03-11T04:56:10Z)
• Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency [3.124750429062221]
  We introduce two new consistency losses that enlarge clusters while preventing them from spreading over distinct objects. The proposed losses are model-independent and can thus be used in a plug-and-play fashion to significantly improve the performance of existing models. We also showcase the effectiveness and generalization capability of our framework on four standard sensor-unique driving datasets.
  arXiv  Detail & Related papers  (2023-12-12T11:00:39Z)
• Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes [82.4186966781934]
  We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules. With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-18T03:48:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.