# Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models

arXiv: https://arxiv.org/abs/2608.25418 · HTML: https://mlsanity.com/paper/2608.25418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 49 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 39)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation](https://mlsanity.com/paper/2008.01550/) (2020)
- [SAMPart3D: Segment Any Part in 3D Objects](https://mlsanity.com/paper/2411.07184/) (2024)
- [PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond](https://mlsanity.com/paper/2504.11451/) (2025)
- [SAI3D: Segment Any Instance in 3D Scenes](https://mlsanity.com/paper/2312.11557/) (2023)
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://mlsanity.com/paper/2208.02812/) (2022)
- [4D Panoptic LiDAR Segmentation](https://mlsanity.com/paper/2102.12472/) (2021)
- [Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data](https://mlsanity.com/paper/2105.08971/) (2021)
- [Point-SAM: Promptable 3D Segmentation Model for Point Clouds](https://mlsanity.com/paper/2406.17741/) (2024)
- [Better Call SAL: Towards Learning to Segment Anything in Lidar](https://mlsanity.com/paper/2403.13129/) (2024)
- [PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation](https://mlsanity.com/paper/2312.03015/) (2023)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation](https://mlsanity.com/paper/2209.14858/) (2022)
- [LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment](https://mlsanity.com/paper/2103.02263/) (2021)
- [Mask4Former: Mask Transformer for 4D Panoptic Segmentation](https://mlsanity.com/paper/2309.16133/) (2023)
- [4D Panoptic Segmentation as Invariant and Equivariant Field Prediction](https://mlsanity.com/paper/2303.15651/) (2023)
- [MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds](https://mlsanity.com/paper/2307.09316/) (2023)
- [AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation](https://mlsanity.com/paper/2308.14936/) (2023)
- [InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data](https://mlsanity.com/paper/2303.03909/) (2023)
- [MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory](https://mlsanity.com/paper/2311.01556/) (2023)

## Abstract (arXiv)

Progress in 4D LiDAR segmentation is bottlenecked by data. Assigning temporally consistent labels across sparse point cloud sequences is costly and hard to scale, and every new task or domain tends to demand fresh dense annotation. This motivates a simple question of whether high-quality LiDAR training data can be produced automatically, without any human labeling. To this end, we introduce LiDAR-SAM2, a framework that turns a 2D video foundation model, SAM2, into a scalable source of supervision for the 4D LiDAR domain. On the data side, it automatically generates temporally coherent LiDAR-level labels from SAM2 video masks through multi-view projection and spatio-temporal aggregation. On the modeling side, a tailored modality interface and a two-stage learning objective adapt SAM2's video segmentation kernel to spatio-temporal LiDAR structure, so that a single click per object yields a consistent mask track across the sequence. Trained with no human LiDAR annotation, LiDAR-SAM2 produces semantic and panoptic labels on SemanticKITTI that approach the quality of full human annotation from only a few points, and models trained on these labels approach the performance of full ground-truth supervision. This positions LiDAR-SAM2 as a scalable labeling tool that substantially reduces the annotation burden for 3D and 4D scene understanding.