arXiv Computer Vision
PnP*: A certifiable solver for Perspective-n-Point
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
1d ago
XM4D: 4D Reconstruction through Certifiable Geometric Optimization
XM4D is a new framework for accurate 4D reconstruction that separates camera motion estimation from non‑rigid deformation. Both stages are cast as structured quadratically constrained quadratic programs (QCQPs) with semidefinite programming (SDP) relaxations, enabling certifiable global optimality. The method uses GPU‑accelerated Burer‑Monteiro solvers, initializes dynamic Gaussian splatting for refinement, and achieves state‑of‑the‑art performance on seven benchmarks.
Hugging Face Trending Papers
1d ago
XM4D: 4D Reconstruction through Certifiable Geometric Optimization
Accurate 4D reconstruction remains challenging: jointly estimating camera motion, scene geometry, and non-rigid deformation entails highly nonconvex optimization, making global optimality difficult to...
arXiv Computer Vision
Aug 24
Robust Validation to Geometric Perturbations for Autonomous Pose Estimation
arXiv:2608.21066v1 Announce Type: new Abstract: Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than...
arXiv Computer Vision
Oct 15
Object Pose from 2-D to 3-D Point and Line Correspondences
arXiv:2610.19734v1 Announce Type: new Abstract: In this paper we present a method for optimally estimating the rotation and translation between a camera and a 3-D object from point and/or line corres...
arXiv Computer Vision
Oct 12
Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence
The paper introduces a new ellipsoid‑specific framework for camera pose estimation from a single ellipse‑ellipsoid correspondence. It shows that the problem can be reduced to either a position‑only or orientation‑only estimation, with the remaining unknowns solvable in closed form, and further to a single degree‑of‑freedom problem with an analytical pose solution. The authors illustrate the theory with visual examples, discuss practical aspects, and provide source code to aid efficient pose estimation.
arXiv AI
Oct 31
Aligning Misaligned Benchmarks for Single-View Novel View Synthesis
The paper addresses the lack of standardized evaluation for single‑view novel view synthesis by highlighting the importance of aligning a method’s reference frame with the ground‑truth camera pose. It proposes using traditional 2D‑to‑2D and 2D‑to‑3D image matching to align 3D reconstructions and restricts evaluation to co‑visible regions where a correct ground truth exists. Experiments show that with proper alignment, 3D Gaussian‑based methods reach state‑of‑the‑art performance, and a simple baseline using a video generator and geometry estimator matches specialized novel‑view synthesis models without task‑specific training.