Absolute-scale 3D human pose estimation from monocular videos via relative depth priors and multi-frame fusion

RC-EndoDepth: Two-stage self-supervised depth and motion estimation with improved scale consistency in endoscopic videos.

Maintaining a stable depth scale across endoscopic video frames remains challenging, which limits downstream applications such as surgical navigation and 3D reconstruction. Existing self-supervised methods often produce accurate relative depth for individual frames but still suffer from scale drift across a video. We p...

GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting

GS-CPE (Gaussian Splatting based Camera Pose Estimation), a coarse-to-fine framework for 6-DoF camera pose estimation that unifies geometry-based coarse pose estimation with robust 3D Gaussian Splatting based pose refinement, is introduced.

Video-based human pose estimation for table tennis: a visual-computing review of datasets, methods, failure modes, and evaluation metrics

VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues

VI3, a model-agnostic framework that metrically anchors a pretrained 3DFM using only IMU readings, is introduced, acting as a fine refinement under well-conditioned motion and as a strong prior when motion is less informative.

MFA-Pose: Human Pose Estimation with Multi-Scale Context Fusion and Adaptive Gated Upsampling for Industrial Surveillance

This paper proposes MFA-Pose, an improved YOLO11s-Pose framework that enhances contextual representation and cross-scale feature reconstruction that provides a favorable balance between pose estimation accuracy and model complexity for industrial surveillance applications.

Monocular Visual-Inertial Odometry via Explicit 3D Motion Modeling

Visual-inertial odometry (VIO) estimates motion by fusing camera and inertial data. In learning-based monocular VIO, depth, scale, and motion are tightly coupled, while IMU cues are difficult to impose as geometric constraints on implicit 2D features. This paper presents a pose estimation method based on explicit 3D mo...