FlexMap: Generalized HD Map Construction from Flexible Camera Configurations
High-definition (HD) maps provide essential semantic information of road structures for autonomous driving systems, yet current HD map construction methods require calibrated multi-camera setups and either implicit or explicit 2D-to-BEV transformations, making them fragile when sensors fail or camera configurations vary across vehicle fleets. We introduce FlexMap, unlike prior methods that are fixed to a specific N-camera rig, our approach adapts to variable camera configurations without any architectural changes or per-configuration retraining. Our key innovation eliminates explicit geometric projections by using a geometry-aware foundation model with cross-frame attention to implicitly encode 3D scene understanding in feature space. FlexMap features two core components: a spatial-temporal enhancement module that separates cross-view spatial reasoning from temporal dynamics, and a camera-aware decoder with latent camera tokens, enabling view-adaptive attention without the need for projection matrices. Experiments demonstrate that FlexMap outperforms existing methods across multiple configurations while maintaining robustness to missing views and sensor variations, enabling more practical real-world deployment.
Code (0)
등록된 구현이 없습니다.
Tasks
Scene UnderstandingAutonomous DrivingSpatial ReasoningSimilar Papers 제목 키워드 기반
A Minimal Solution to the Generalized Pose-and-Scale Problem
We propose a novel solution to the generalized camera pose problem which includes the internal scale of the generalized camera as an unknown parameter. This further generalization of the well-known absolute camera pose …
Monocular Visual OdometryMotion EstimationVisual OdometryPartially calibrated semi-generalized pose from hybrid point correspondences
In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t. a generalized camera, from a hybrid set…
GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction
Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs, visual plausibility is insufficient: th…
3D ReconstructionSix-Point Method for Multi-Camera Systems with Reduced Solution Space
Relative pose estimation using point correspondences (PC) is a widely used technique. A minimal configuration of six PCs is required for two views of generalized cameras. In this paper, we present several minimal solvers…
Pose EstimationTranslationReal-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination
We propose a novel framework for real-time acquisition and reconstruction of temporally-varying 3D phenomena with high quality. The core of our framework is a deep neural network with an encoder that directly maps to…
Decoder