2026-08-07 · IROS 2026

Vernata: Self-Supervised Learning of LiDAR Point Representations

Oliver Lemke, Alexander Liniger, Abel Gawel, Marco Hutter

Published at IROS 2026. 0 citations, as of the last refresh.

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.

arXiv comment: IROS 2026. Implementation: https://github.com/rai-opensource/vernata

Ten-minute slide kit

Six slides is the whole talk: what was broken, what people tried, what these authors did, what the numbers say, where it falls over, and the sentence people should remember.

SLIDE 1

The problem

Autonomous robots are increasingly transitioning from research demonstrations in controlled environments to operating in the unstructured real world , . This progress is underpinned by advancements in scene understanding, which equip agents with the semantic context required to perform complex, intelligent actions in unstructured environments –. LiDAR sensors are central to this advanced perception

SLIDE 2

What came before

Motivated by findings that model performance scales effectively with data and compute –, the field has increasingly adopted selfsupervised learning. Learning representations directly from raw data, SSL allows models to utilize massive unlabeled datasets for scaling . Early approaches largely relied on contrastive objectives, such as SimCLR and MoCo , which enforce feature invariance across augmented views of the same sample, while pushing apart representations from different

SLIDE 3

The method

We present Vernata, a multi-modal, multi-teacher distillation framework designed to learn robust point representations from LiDAR data. Building upon Sonata , our approach introduces three extensions to overcome inherent density variations and limited semantic cues in outdoor LiDAR, as well as the practical bottleneck of resource-constrained training. Architecturally, Sonata adapts a DINOv2-style selfdistillation framework to the 3D domain. It employs a dual-network structure consisting of a student and a teacher…

SLIDE 4

What they measured

We evaluate our framework across two domains: unstructured field environments and urban driving. In the former, we combine the real-world GrandTour and synthetic TartanGround for self-supervised pretraining. However, as GrandTour lacks semantic annotations, we perform downstream evaluation exclusively on TartanGround. For the latter, we utilize the Waymo Open Dataset as a selfcontained benchmark, employing it for both pretraining and evaluation to validate our method on an established

SLIDE 5

Where it breaks

Not recoverable from the parsed text. Read this section in the paper yourself.

SLIDE 6

One-line takeaway

Vernata is introduced, 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.

Assembled from the paper's own PDF, parsed with its layout intact so tables and equations survive, 45,552 characters of it, then split on the paper's own section headings. Extractive, not generated: every sentence here is lifted from the paper. Check it before you present it.