Vision-Based Relative Pose Estimation of Space Objects for Proximity Operations Using Lab-Validated Deep Learning

DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching

A novel framework for single-shot shape and pose estimation of unknown spacecraft objects using only a single image and reconstructed geometry is proposed, demonstrating strong generalization to unseen spacecraft.

Depth-Augmented Pose Tracking for Autonomous Robots: A Filter-based Multi-Sensor Fusion Approach

Robotic platforms operating in GPS-denied environments require robust ego-motion estimation systems that fuse complementary sensor modalities under onboard computational constraints. This paper proposes a navigation framework estimating six-degree-of-freedom (6 DoF) robot pose in unstructured scenes using a monocular camera stream, inertial measurement unit (IMU) data, and sparse depth cues within the multi-state constraint Kalman filter (MSCKF) architecture. The key innovation integrates 3D landmark measurements into visual feature tracks, reducing positional uncertainty and drift accumulation compared to vision-only approaches. The method is efficient enough for resource-constrained systems such as micro aerial vehicles and small ground robots. The measurement fusion strategy is analytically derived and evaluated on aerial robot trajectory datasets. Results show improved tracking accuracy and stability in challenging indoor and outdoor scenarios without GPS, enabling prolonged autonomous missions in complex 3D environments with real-time pose feedback and low computational burden.

Accurate 6D pose estimation using consumer-grade depth cameras in real-world scenarios

Real-Time Temporally Consistent Monocular 6D UAV Pose Estimation for Onboard Aerial Perception

The precision of 6D pose estimation is crucial for autonomous UAV perception, tracking, and navigation. Recent monocular pose estimation methods have shown encouraging results, but they are based on individual frames and do not fully utilize the temporal continuity in video sequences. As a result, even though pose estimation can be performed in a monocular manner, it can suffer from temporal jitter, unstable trajectories, and orientation ambiguity in fast motion, partial occlusions and challenging perspectives. To address these problems, AeroMotion6D is proposed, a temporal transformer-based framework for monocular UAV 6D pose estimation from RGB video. The suggested framework consists of an adaptive context fusion (ACF) mechanism that can incorporate past context information into the current estimation process and a persistent pose memory (PPM) module that can convey pose-related information in two consecutive frames. A symmetry-aware learning strategy is created to resolve orientation ambiguities in partially symmetric UAVs, and a motion-aware learning objective is created to promote pose evolution over time. AeroMotion6D continuously outperforms representative state-of-the-art techniques, according to experimental evaluations on public benchmarks; it achieves a mean absolute rotation error (MAEr) of 15.92∘ and a translation of 0.202 m on the DroneKey benchmark, and an average precision (AP) of 98.12% with a strict 10∘/10 cm success rate of 75.84% on the MAV6D benchmark. Furthermore, real-world validation on a physical Quanser QDrone platform confirms high robustness and practical applicability, yielding an average rotation error of 11.42∘, an average translation error of 0.141 m, and a 10∘/10 cm success rate of 87.53%. Embedded implementation experiments using an NVIDIA Jetson Orin NX with TensorRT FP16 optimization achieve real-time operation at approximately 17 FPS with an end-to-end latency of ∼58 ms per frame, demonstrating the practical onboard applicability of the proposed framework.

DAP-Pose: Deep Temporal Alignment and Physics-aware Cross-modal Sensor Fusion for Robust Pose Estimation

Robust and accurate pose estimation with multi-modal sensors is fundamental for autonomous vehicles and mobile robotic systems in complex environments. In this paper, we propose DAP-Pose, a unified end-to-end model for robust multi-modal pose estimation. DAP-Pose introduces a Bi-level Cross-modal Fusion (BCF) module that captures complementary semantic and geometric motion cues from visual, inertial, and GNSS measurements. To handle temporal offsets, we designed a Deep Temporal Alignment (DTA) module that explicitly aligns asynchronous streams in latent space, enabling coherent motion modeling without strict hardware synchronization. Furthermore, we incorporate physics-aware constraints via manifold geometry and GNSS-guided absolute metric scale, enforcing motion consistency and mitigating drift. Experiments upon the public KITTI benchmark dataset were conducted to evaluate the performance of DAP-Pose against existing methods. DAP-Pose achieved the state-of-the-art performance, with the lowest average translation error ($t_{rel}$) of 1.31% and rotation error ($r_{rel}$) of 0.46$^{\circ}$. Furthermore, it accurately estimates poses and maintains robust performance under severe artificially injected temporal misalignment.

DOU-Pose: Robust Camera-Based Visual Localization for Autonomous Vehicles in Repetitive and Low-Texture Intelligent Transportation Environments

Accurate and robust vehicle localization is essential for autonomous driving. However, existing visual pose estimation methods often struggle in scenarios dominated by repetitive structures or sparse textures. These conditions lead to ambiguous predictions of 3D scene coordinates and a high proportion of structured outliers—erroneous predictions forming coherent clusters that deceive standard estimators. To address these limitations, this paper proposes DOU-Pose (Depthwise Over-parameterized U-shaped Pose estimation), a visual pose estimation framework built upon the Differentiable SAmple Consensus (DSAC)* pipeline. The core idea is to enhance the discriminative capability of scene coordinate regression through improved feature extraction. Specifically, we replace standard convolutional layers with Depthwise Over-parameterized Convolution (DO-Conv), which introduces auxiliary learnable depthwise kernels during training to enrich the representational capacity of the network, while allowing their fusion into a single kernel for inference. Furthermore, a U-shaped regression network with transposed convolutions is designed to preserve spatial details and strengthen fine-grained geometric reasoning. The entire pipeline is trained end-to-end by coupling dense scene coordinate prediction with a differentiable robust estimator. Extensive experiments demonstrate that DOU-Pose achieves competitive performance on public benchmarks and clear robustness improvements on the self-collected Campus-AV dataset, especially in repetitive and low-texture outdoor driving scenarios.