Vernata: Self-Supervised Learning of LiDAR Point Representations

• URL: http://arxiv.org/abs/2608.06919v1
• Date: Fri, 07 Aug 2026 07:51:39 GMT
• Title: Vernata: Self-Supervised Learning of LiDAR Point Representations
• Abstract summary: We present a multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds.<n>Our experiments demonstrate a significant performance improvement over Sonata baselines.<n>We show that the self-supervised approach maintains strong performance even in reduced-modality settings.
• Score: 47.91691222306441
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR serves as a primary sensing modality for robots operating in outdoor environments. However, the performance of deep learning models in this domain is severely limited by the scarcity of labeled data, a direct result of the high cost of 3D annotation. Self-supervised learning addresses this scarcity by learning general-purpose features from unlabeled data. In this work, we present a multi-modal, multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds. Building upon the Sonata architecture, we introduce Vernata, consisting of three extensions: sparse view augmentation to improve robustness against varying point densities, a memory bank mechanism to stabilize resource-constrained training, and cross-modal distillation utilizing dense, high-resolution 2D image features to enable fine-grained semantic guidance. We evaluate our method on the GrandTour, TartanGround, and Waymo datasets, as well as data collected from our own robotic platforms. Our experiments demonstrate a significant performance improvement over Sonata baselines, yielding mIoU scores of 54.7 on TartanGround (+5.9 points, +12.1%) and 57.1 on Waymo (+7.3 points, +14.7%). Finally, we show that the self-supervised approach maintains strong performance even in reduced-modality settings (lacking color or normals), achieving competitive mIoU scores of 49.4 and 50.2 on the respective datasets.

Related papers

• Self-Improving 4D Perception via Self-Distillation [49.729154812786696]
  SelfEvo is a self-trained framework that continually improves pre-trained multiview reconstruction using untruth videos.<n>We systematically study design choices that make self-improvement effective, including loss signals, forms of asymmetry, and other training strategies.<n>Overall, SelfEvo achieves up to 36.5% relative improvement in video depth estimation and 20.1% in camera estimation, without using any labeled data.
  arXiv  Detail & Related papers  (2026-04-09T17:59:04Z)
• PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning [5.308328605042682]
  360 panoramic images are increasingly used in virtual reality, autonomous driving, and robotics for holistic scene understanding.<n>Current Vision-Language Models (VLMs) struggle with 3D spatial reasoning on Equirectangular Projection (ERP) images due to geometric distortion and limited 3D supervision.<n>We introduce PanoEnv, a large-scale VQA benchmark built from synthetic 3D environments.<n>Our 7B model achieves new state-of-the-art performance, improving overall accuracy to 52.93% (+3.59%) and open-ended accuracy to 14.83% while maintaining structured-task performance.
  arXiv  Detail & Related papers  (2026-02-25T15:12:17Z)
• Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration [72.84714132070404]
  We propose a framework that shifts from passive interaction to active exploration of visual environments.<n>Active-Zero employs three co-evolving agents: a Searcher that retrieves images from open-world repositories based on the model's capability frontier.<n>On Qwen2.5-VL-7B-Instruct across 12 benchmarks, Active-Zero 53.97 average accuracy on reasoning tasks (5.7% improvement) and 59.77 on general understanding (3.9% improvement)
  arXiv  Detail & Related papers  (2026-02-11T17:29:17Z)
• STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision [24.162895928364062]
  We introduce STELAR-Vision, a training framework for topology-aware reasoning.<n>At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures.<n>On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%.
  arXiv  Detail & Related papers  (2025-08-12T07:27:50Z)
• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO)<n>In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery.<n>We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding [39.967352995143855]
  GroundingSuite aims to bridge the gap between vision and language modalities.<n>It comprises: (1) an automated data annotation framework leveraging multiple Vision-Language Model (VLM) agents; (2) a large-scale training dataset encompassing 9.56 million diverse referring expressions and their corresponding segmentations; and (3) a meticulously curated evaluation benchmark consisting of 3,800 images.<n>The GroundingSuite training dataset facilitates substantial performance improvements, enabling models trained on it to achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2025-03-13T17:43:10Z)
• 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)
• 3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving [17.42913935045091]
  We propose AFOV, a novel 3D textbfAnnotation-textbfFree framework assisted by 2D textbfOpen-textbfVocabulary segmentation models.<n>It consists of two stages: In the first stage, we innovatively integrate high-quality textual and image features of 2D open-vocabulary models and propose the Tri-Modal contrastive Pre-training (TMP)<n>In the second stage, spatial mapping between point clouds and images is utilized to generate pseudo-labels, enabling cross
  arXiv  Detail & Related papers  (2024-05-24T07:18:09Z)
• Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving [58.16024314532443]
  We introduce LaserMix++, a framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to assist data-efficient learning.<n>Results demonstrate that LaserMix++ outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations.<n>This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.
  arXiv  Detail & Related papers  (2024-05-08T17:59:53Z)
• SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations [76.45009891152178]
  Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks.<n>We show, for the first time, that general representations learning can be achieved through the task of occupancy prediction.<n>Our findings will facilitate the understanding of LiDAR points and pave the way for future advancements in LiDAR pre-training.
  arXiv  Detail & Related papers  (2023-09-19T11:13:01Z)
• Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning [2.16117348324501]
  We propose a novel semi-supervised active learning (SSAL) framework for monocular 3D object detection with LiDAR guidance (MonoLiG) We utilize LiDAR to guide the data selection and training of monocular 3D detectors without introducing any overhead in the inference phase. Our training strategy attains the top place in KITTI 3D and birds-eye-view (BEV) monocular object detection official benchmarks by improving the BEV Average Precision (AP) by 2.02.
  arXiv  Detail & Related papers  (2023-07-17T11:55:27Z)

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.