Data annotation in autonomous vehicles is a critical step in the development of Deep Neural Network (DNN) based models or the performance evaluation of the perception system. This often takes the form of adding 3D bounding boxes on time-sequential and registered series of point-sets captured from active sensors like Light Detection and Ranging (LiDAR) and Radio Detection and Ranging (RADAR). When annotating multiple active sensors, there is a need to motion compensate and translate the points to a consistent coordinate frame and timestamp respectively. However, highly dynamic objects pose a unique challenge, as they can appear at different timestamps in each sensor's data. Without knowing the speed of the objects, their position appears to be different in different sensor outputs. Thus, even after motion compensation, highly dynamic objects are not matched from multiple sensors in the same frame, and human annotators struggle to add unique bounding boxes that capture all objects. This article focuses on addressing this challenge, primarily within the context of Scania-collected datasets. The proposed solution takes a track of an annotated object as input and uses the Moving Horizon Estimation (MHE) to robustly estimate its speed. The estimated speed profile is utilized to correct the position of the annotated box and add boxes to object clusters missed by the original annotation.

LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused by ego motion, distortions caused by other moving objects remain largely overlooked, leading to errors in object shape and position. This distortion is particularly pronounced in high-speed environments such as highways and in multi-LiDAR configurations, a common setup for heavy vehicles. To address this challenge, we introduce HiMo, a pipeline that repurposes scene flow estimation for non-ego motion compensation, correcting the representation of dynamic objects in point clouds. During the development of HiMo, we observed that existing self-supervised scene flow estimators often produce degenerate or inconsistent estimates under high-speed distortion. We further propose SeFlow++, a real-time scene flow estimator that achieves state-of-the-art performance on both scene flow and motion compensation. Since well-established motion distortion metrics are absent in the literature, we introduce two evaluation metrics: compensation accuracy at a point level and shape similarity of objects. We validate HiMo through extensive experiments on Argoverse 2, ZOD and a newly collected real-world dataset featuring highway driving and multi-LiDAR-equipped heavy vehicles. Our findings show that HiMo improves the geometric consistency and visual fidelity of dynamic objects in LiDAR point clouds, benefiting downstream tasks such as semantic segmentation and 3D detection. See https://kin-zhang.github.io/HiMo for more details.

3D object detection at long-range is crucial for ensuring the safety and efficiency of self-driving vehicles, allowing them to accurately perceive and react to objects, obstacles, and potential hazards from a distance. But most current state-of-the-art LiDAR based methods are range limited due to sparsity at long-range, which generates a form of domain gap between points closer to and farther away from the ego vehicle. Another related problem is the label imbalance for faraway objects, which inhibits the performance of Deep Neural Networks at long-range. To address the above limitations, we investigate two ways to improve long-range performance of current LiDAR-based 3D detectors. First, we combine two 3D detection networks, referred to as range experts, one specializing at near to mid-range objects, and one at long-range 3D detection. To train a detector at long-range under a scarce label regime, we further weigh the loss according to the labelled point's distance from ego vehicle. Second, we augment LiDAR scans with virtual points generated using Multimodal Virtual Points (MVP), a readily available image-based depth completion algorithm. Our experiments on the long-range Argoverse2 (AV2) dataset indicate that MVP is more effective in improving long range performance, while maintaining a straightforward implementation. On the other hand, the range experts offer a computationally efficient and simpler alternative, avoiding dependency on image-based segmentation networks and perfect camera-LiDAR calibration.

Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away. Although significant advancements have been made in scene flow pipelines to handle large-scale point clouds, a gap remains in scalability with respect to long-range. We attribute this limitation to the common design choice of using dense feature grids, which scale quadratically with range. In this paper, we propose Sparse Scene Flow (SSF), a general pipeline for long-range scene flow, adopting a sparse convolution based backbone for feature extraction. This approach introduces a new challenge: a mismatch in size and ordering of sparse feature maps between time-sequential point scans. To address this, we propose a sparse feature fusion scheme, that augments the feature maps with virtual voxels at missing locations. Additionally, we propose a range-wise metric that implicitly gives greater importance to faraway points. Our method, SSF, achieves state-of-the-art results on the Argoverse2 dataset, demonstrating strong performance in long-range scene flow estimation. Our code is open-sourced at https://github.com/KTH-RPL/SSF.git.

Accurate 3D scene flow estimation is critical for autonomous systems to navigate dynamic environments safely, but creating the necessary large-scale, manually annotated datasets remains a significant bottleneck for developing robust perception models. Current self-supervised methods struggle to match the performance of fully supervised approaches, especially in challenging long-range and adverse weather scenarios, while supervised methods are not scalable due to their reliance on expensive human labeling. We introduce DoGFlow, a novel selfsupervised framework that recovers full 3D object motions for LiDAR scene flow estimation without requiring any manual ground truth annotations. This paper presents our cross-modal label transfer approach, where DoGFlow computes motion labels directly from 4D radar Doppler measurements and transfers them to the LiDAR domain using dynamic-aware association and ambiguity-resolved propagation. On the challenging MAN TruckScenes dataset, DoGFlow substantially outperforms existing self-supervised methods and improves label efficiency by enabling LiDAR backbones to achieve over 90% of fully supervised performance with only 10% of the ground truth data. For more details including supplementary material, please visit https://ajinkyakhoche.github.io/DoGFlow/.

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however itis often hindered by a significant domain gap betweenthe synthetic data used for training and the sparse, noisyLiDAR scans encountered in the real-world. Currentmethods trained solely on synthetic data fail to general-ize to outdoor scenes, while those trained only on realdata lack the semantic diversity to recognize rare or un-seen objects. We introduce BlendCLIP, a multimodalpretraining framework that bridges this synthetic-to-realgap by strategically combining the strengths of both do-mains. We first propose a pipeline to generate a large-scale dataset of object-level triplets—consisting of a pointcloud, image, and text description—mined directly fromreal-world driving data and human annotated 3D boxes.Our core contribution is a curriculum-based data mix-ing strategy that first grounds the model in the semanti-cally rich synthetic CAD data before progressively adapt-ing it to the specific characteristics of real-world scans.Our experiments show that our approach is highly label-efficient: introducing as few as 1.5% real-world samplesper batch into training boosts zero-shot accuracy on thenuScenes benchmark by 27%. Consequently, our finalmodel achieves state-of-the-art performance on challeng-ing outdoor datasets like nuScenes and TruckScenes, im-proving over the best prior method by 19.3% on nuScenes,while maintaining strong generalization on diverse syn-thetic benchmarks. Our findings demonstrate that effectivedomain adaptation, not full-scale real-world annotation, isthe key to unlocking robust open-vocabulary 3D perception.Our code and dataset will be released upon acceptance onhttps://github.com/kesu1/BlendCLIP.