camera projection estimation

This work proposes PnP-ProCay78, a novel algorithm addressing the accuracy and efficiency challenges in initial pose estimation for the planar Perspective-n-Point (PnP) problem. The method introduces a geometrically transparent and computationally efficient hybrid cost function that innovatively combines projection error minimization with a proxy term for translation reconstruction error derived via analytical elimination. Rotation is parameterized using the Cayley representation, and deterministic initialization coupled with least-squares optimization eliminates the need for costly search procedures. Theoretical analysis reveals convergence properties of the optimization trajectory within Cayley space. Experimental results demonstrate that the algorithm achieves projection accuracy comparable to SQPnP and slightly superior to IPPE on both RGB and low-resolution thermal imaging data, while maintaining a more streamlined structure.

This work proposes a novel method for establishing point correspondences across image sequences in real time under unknown 3D scene structure and imaging geometry. The approach introduces a channel-vector-based uncertainty density model and employs an online optimization mechanism driven by Neyman chi-square divergence to iteratively learn mappings between image point sets. By representing channel vectors with basis functions and integrating a density divergence criterion, the algorithm achieves rapid convergence and high-accuracy correspondence estimation under general imaging geometries. Experimental results demonstrate that the proposed method outperforms state-of-the-art techniques across multiple metrics, offering a compelling combination of real-time performance, robustness, and accuracy.

This paper addresses the relative pose estimation problem for three calibrated cameras given only four correspondences across all views. To overcome limitations of conventional methods—namely, their reliance on more correspondences or insufficient robustness—we propose a novel strategy that approximates a fifth correspondence using the centroid of the four observed points. We further introduce the first joint three-view pose estimation framework integrating a 4-point affine fundamental matrix solver, a standard 5-point relative pose solver, and a P3P solver. Geometric modeling enhances robustness against noise and outliers, while local optimization refines accuracy. Evaluated on real-world datasets, our method achieves state-of-the-art performance: the centroid-based strategy significantly outperforms pure affine approaches, striking a superior balance among accuracy, robustness, and computational efficiency, with straightforward implementation.

In multi-view 3D reconstruction, photometric distortions—such as vignetting and lens contamination—degrade scene representation fidelity. To address this, we propose a novel joint optimization framework that simultaneously learns both the 3D radiance field and camera-specific photometric models. Our approach introduces an explicit parametrization of intrinsic and extrinsic photometric effects, tightly coupling differentiable rendering with depth-based regularization to disentangle imaging distortions from underlying scene geometry and appearance. During training, radiance field parameters and photometric correction parameters are co-optimized, effectively suppressing the adverse impact of imaging noise on reconstruction accuracy. Experiments demonstrate that our method significantly improves reconstruction fidelity and robustness under photometric degradation, outperforming conventional methods that ignore photometric modeling. It achieves state-of-the-art performance across multiple standard benchmarks.

This paper addresses camera motion estimation from two-view 2D point correspondences. Departing from conventional suboptimal formulations based on the essential matrix and epipolar constraints, it directly formulates maximum-likelihood estimation on the SO(3) × S² manifold for rotation and normalized translation. The proposed algorithm is the first to achieve both statistical consistency and asymptotic efficiency—its mean-square error attains the Cramér–Rao lower bound. It combines noise-variance-adaptive initialization, bias correction, and a single-step Gauss–Newton optimization on the manifold, yielding O(n) time complexity. Evaluated on synthetic and real-world datasets with hundreds of point correspondences, the method outperforms state-of-the-art approaches in both accuracy and CPU runtime. Extensive experiments validate its theoretical guarantees and practical efficacy.

This work addresses the challenges of missing correspondences and incomplete geometric information in point cloud reconstruction from partially observed multi-view inputs. The authors propose a training-free optimization method that jointly recovers the 3D point cloud and its cross-view projection mappings. Built upon an extended multi-view synchronized embedding framework, the approach integrates variable projection, geometric constraints, and visibility modeling, making it applicable to both fixed and variable projection settings without requiring category-specific priors. Experiments on ShapeNet and Pix3D demonstrate that the method robustly reconstructs partial multi-view point clouds, consistently outperforming existing non-learning baselines across Chamfer distance, Earth Mover’s Distance (EMD), and Reconstruction Overlap Accuracy (ROA) metrics.

This work proposes a novel approach to generic camera calibration under motion blur, a condition that typically degrades accuracy due to reliance on sharp images. The method jointly estimates feature point locations and spatially varying point spread functions (PSFs) directly from blurred images—marking the first integration of blurred feature localization and PSF estimation within generic camera calibration. By incorporating geometric constraints and a locally parameterized illumination model, the approach effectively models translational blur and resolves the ambiguities it introduces. Experimental results demonstrate that the proposed technique achieves high-precision calibration even in the presence of significant motion blur, thereby extending the applicability of generic calibration methods to more challenging real-world imaging conditions.

This work addresses the problem of establishing affine transformation relationships between local image patches observed by two calibrated cameras. By integrating multi-view geometry with differential geometric analysis, the authors derive the first closed-form solution for the affine transformation that is valid for arbitrary calibrated camera pairs. The solution explicitly characterizes the analytical dependence of the transformation on the relative pose, image coordinates, and local surface normal. The proposed method is not only concise in formulation and computationally efficient but also provides a rigorous theoretical foundation for applications such as image registration, feature matching, and 3D reconstruction.

This work addresses the limitations of existing monocular 3D Morphable Model (3DMM) regression methods in reconstructing near-range facial images—such as those captured by head-mounted cameras—where the use of orthographic projection fails to account for perspective distortion, leading to geometric inaccuracies. To mitigate this issue, the authors propose an extended orthographic projection model augmented with a shrinkage parameter that effectively approximates pseudo-perspective effects while preserving training stability. The proposed formulation is readily integrated into existing 3DMM regression frameworks through direct fine-tuning, without requiring architectural overhauls. Experimental results on a newly collected head-mounted camera dataset demonstrate that the method significantly outperforms conventional orthographic projection in both quantitative metrics and qualitative visual fidelity, yielding more accurate and realistic 3D facial reconstructions at close range.

This work addresses the significant performance degradation of existing 3D reconstruction methods on non-pinhole imagery—such as fisheye or panoramic views—due to their reliance on the pinhole camera assumption. To overcome this limitation, we propose the first feed-forward, calibration-free, universal 3D reconstruction framework capable of handling diverse camera models. Our approach employs a dual-branch network to jointly estimate per-pixel ray directions and radial distances, complemented by a ray-aware global alignment mechanism that fuses local geometric cues while simultaneously optimizing pose and scale. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both 3D reconstruction and pose estimation across fisheye, panoramic, and pinhole image datasets, marking the first unified, calibration-free solution for cross-camera-model 3D reconstruction.