# LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applications

arXiv: https://arxiv.org/abs/2509.05728 · HTML: https://mlsanity.com/paper/2509.05728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 6 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [VideoLCM: Video Latent Consistency Model](https://mlsanity.com/paper/2312.09109/) (2023)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://mlsanity.com/paper/2407.16124/) (2024)
- [Temporally Consistent Transformers for Video Generation](https://mlsanity.com/paper/2210.02396/) (2022)
- [MoVideo: Motion-Aware Video Generation with Diffusion Models](https://mlsanity.com/paper/2311.11325/) (2023)
- [Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss](https://mlsanity.com/paper/2501.07563/) (2025)
- [T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning](https://mlsanity.com/paper/2312.10217/) (2023)
- [Temporally-Consistent Bilinearly Recurrent Autoencoders for Control Systems](https://mlsanity.com/paper/2503.19085/) (2025)
- [Hybrid Temporal Differential Consistency Autoencoder for Efficient and Sustainable Anomaly Detection in Cyber-Physical Systems](https://mlsanity.com/paper/2504.06320/) (2025)

## Abstract (arXiv)

This paper extends LiDAR-BIND, a modular multi-modal fusion framework that binds heterogeneous sensors (radar, sonar) to a LiDAR-defined latent space, with mechanisms that explicitly enforce temporal consistency. We introduce three contributions: (i) temporal embedding similarity that aligns consecutive latent representations, (ii) a motion-aligned transformation loss that matches displacement between predictions and ground truth LiDAR, and (iii) windowed temporal fusion using a specialised temporal module. We further update the model architecture to better preserve spatial structure. Evaluations on radar/sonar-to-LiDAR translation demonstrate improved temporal and spatial coherence, yielding lower absolute trajectory error and better occupancy map accuracy in Cartographer-based SLAM (Simultaneous Localisation and Mapping). We propose different metrics based on the Fr'echet Video Motion Distance (FVMD) and a correlation-peak distance metric providing practical temporal quality indicators to evaluate SLAM performance. The proposed temporal LiDAR-BIND, or LiDAR-BIND-T, maintains modular modality fusion while substantially enhancing temporal stability, resulting in improved robustness and performance for downstream SLAM.