TL;DR
InCaRPose is a Transformer-based model that estimates relative camera pose in in-cabin environments, enabling accurate, real-time extrinsic calibration using synthetic training data and generalizing well to real-world scenarios.
Contribution
The paper introduces a novel Transformer architecture for robust relative pose estimation in highly distorted in-cabin environments, trained solely on synthetic data, with real-world applicability.
Findings
Achieves absolute metric-scale translation in a single inference step.
Generalizes to real-world cabin environments without exact intrinsics.
Maintains high precision in rotation and translation with limited training data.
Abstract
Camera extrinsic calibration is a fundamental task in computer vision. However, precise relative pose estimation in constrained, highly distorted environments, such as in-cabin automotive monitoring (ICAM), remains challenging. We present InCaRPose, a Transformer-based architecture designed for robust relative pose prediction between image pairs, which can be used for camera extrinsic calibration. By leveraging frozen backbone features such as DINOv3 and a Transformer-based decoder, our model effectively captures the geometric relationship between a reference and a target view. Unlike traditional methods, our approach achieves absolute metric-scale translation within the physically plausible adjustment range of in-cabin camera mounts in a single inference step, which is critical for ICAM, where accurate real-world distances are required for safety-relevant perception. We specifically…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
