Minimalist Visual Inertial Odometry
Summary
A minimalist visual-inertial odometry approach uses four photodiodes with optical Gabor masks and a temporal convolutional network to achieve accurate planar motion estimation for differential-drive robots, validated across diverse indoor and outdoor terrains without real-world fine-tuning.
View Cached Full Text
Cached at: 05/22/26, 10:19 AM
Paper page - Minimalist Visual Inertial Odometry
Source: https://huggingface.co/papers/2605.19990
Abstract
A minimalist visual-inertial odometry approach uses four photodiodes with optical Gabor masks and a temporal convolutional network to achieve accurate planar motion estimation for differential-drive robots.
Visual-Inertial Odometry(VIO), which is critical to mobile robot navigation, uses cameras with a large number of pixels. Capturing and processing camera images requires significant resources. This work presents a minimalist approach to planar odometry, demonstrating that just four visual measurements and an IMU can provide robust motion estimation fordifferential-drive robots. Our key insight is that four downward-facingphotodiodesthat sense the world throughoptical Gabor masksproduce signals that encode speed. Based on this, we jointly optimize the mask parameters alongside aTemporal Convolutional Network(TCN) using aphysically-grounded simulator. The resulting model decodes speed from just the four measurements produced by thephotodiodes. Pairing these estimates with the angular speed from an IMU yields a continuous planar trajectory. We validate our approach with a prototype sensor mounted on a differential drive robot. Across diverse indoor and outdoor terrains, our system closely tracks the reference ground truth without any real-world fine-tuning. Our work shows that minimalist sensing enables efficient and accurate planar odometry.
View arXiv pageView PDFProject pageGitHub4Add to collection
Get this paper in your agent:
hf papers read 2605\.19990
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.19990 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.19990 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.19990 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Proposes physical self-supervised learning, an autoencoder paradigm for label-free IMU sensing that replaces the neural decoder with a physics-based decoder, achieving up to 5x error reduction in tracking and motion capture tasks without manual labels.
Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition
This paper introduces Dynamic Influence Weighting (DIW), a knowledge distillation method that improves single-IMU activity recognition by dynamically weighting teacher targets from multiple IMUs during training, achieving significant performance gains.
Inertia-1: An Open Exploration to a Unified Motion Foundation Model
Inertia-1 is a research project that systematically explores the full lifecycle of motion models—data, sensing, objectives, and scale—to produce a unified representation that transfers across body placements, devices, and tasks without retraining, leveraging self-supervised pretraining on 18 million hours of accelerometry data.
LIMMT: Less is More for Motion Tracking
This paper introduces LIMMT, a data-centric study showing that training with high-quality, minimal subsets of motion data (under 3% of AMASS) outperforms using the full dataset for physics-based humanoid motion tracking, defining motion data quality through physics feasibility, diversity, and complexity.