Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment

• URL: http://arxiv.org/abs/2405.05079v5
• Date: Tue, 13 Aug 2024 13:25:34 GMT
• Title: Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment
• Abstract summary: We introduce Power Variable Projection (PoVar) to solve small-scale Bundle Adjustment problems. We experimentally demonstrate that our solver achieves state-of-the-art results in terms of speed and accuracy.
• Score: 39.997922776362174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most Bundle Adjustment (BA) solvers like the Levenberg-Marquardt algorithm require a good initialization. Instead, initialization-free BA remains a largely uncharted territory. The under-explored Variable Projection algorithm (VarPro) exhibits a wide convergence basin even without initialization. Coupled with object space error formulation, recent works have shown its ability to solve small-scale initialization-free bundle adjustment problem. To make such initialization-free BA approaches scalable, we introduce Power Variable Projection (PoVar), extending a recent inverse expansion method based on power series. Importantly, we link the power series expansion to Riemannian manifold optimization. This projective framework is crucial to solve large-scale bundle adjustment problems without initialization. Using the real-world BAL dataset, we experimentally demonstrate that our solver achieves state-of-the-art results in terms of speed and accuracy. To our knowledge, this work is the first to address the scalability of BA without initialization opening new venues for initialization-free structure-from-motion.

Related papers

• Initialization-Free Bundle Adjustment Revisited: A Controlled Experimental Study [55.50399455527231]
  Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations.<n>Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations.<n>We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator.
  arXiv  Detail & Related papers  (2026-08-18T17:23:06Z)
• A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks [0.0]
  In "reservoir computing", the weights of a readout are learned linearly while the reservoir weights are fixed and largely determine the richness, stability and memory of the resulting dynamics.<n>In the infinite-width limit it has been shown that meaningful initializations are those sitting at an effective critical point of the randomly layer model.<n>Here we derive a simple criterion to estimate the critical $g_c$ for a broad class of recurrent architectures and we show that it closely tracks the gain at which a gated-RNN reservoir achieves peak performance on a chaotic forecasting task.
  arXiv  Detail & Related papers  (2026-05-11T14:35:22Z)
• Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks [5.363441578662801]
  Improper weight training of ReLU networks can cause inactivation dying ReLU and exacerbate instability as network depth increases.<n>We introduce an optimization problem on the Stiefel manifold, thereby preserving scale and calibrating the pre-activation statistics.<n>We show that prevention of the dying ReLU problem, slower decay of activation variance, and mitigation of gradient vanishing, which together stabilize signal and gradient flow in deep architectures.
  arXiv  Detail & Related papers  (2025-08-30T05:17:31Z)
• ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints [64.35580479051208]
  In previous works, low-rank adapters (LoRA) are randomly with a fixed rank across all attachment points.<n>In this paper, we improve convergence and final performance of LoRA fine-tuning using our proposed data-driven weight initialization method.
  arXiv  Detail & Related papers  (2025-07-09T23:52:31Z)
• Improving Monocular Visual-Inertial Initialization with Structureless Visual-Inertial Bundle Adjustment [0.36868085124383626]
  We propose a structureless visual-inertial bundle adjustment to further refine previous structureless solution. Experiments on real-world datasets show our method significantly improves the VIO initialization accuracy, while maintaining real-time performance.
  arXiv  Detail & Related papers  (2025-02-23T14:55:40Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• On the Crucial Role of Initialization for Matrix Factorization [40.834791383134416]
  This work revisits the classical lowrank matrix factorization problem and unveils the critical role of initialization in shaping convergence rates. We introduce Nystrom NyGD in both symmetric asymmetric matrix factorization tasks and extend this to low-rank adapters (LoRA) Our approach, NoRA, demonstrates superior performance across various downstream and model scales, from 1B to 7B parameters, in large language and diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T17:58:21Z)
• Smooth over-parameterized solvers for non-smooth structured optimization [3.756550107432323]
  Non-smoothness encodes structural constraints on the solutions, such as sparsity, group sparsity, low-rank edges and sharp edges. We operate a non-weighted but smooth overparametrization of the underlying nonsmooth optimization problems. Our main contribution is to apply the Variable Projection (VarPro) which defines a new formulation by explicitly minimizing over part of the variables.
  arXiv  Detail & Related papers  (2022-05-03T09:23:07Z)
• Power Bundle Adjustment for Large-Scale 3D Reconstruction [47.08614319083826]
  We introduce Power Bundle Adjustment as an expansion type algorithm for solving large-scale bundle adjustment problems. It is based on the power series expansion of the inverse Schur complement and constitutes a new family of solvers that we call inverse expansion methods.
  arXiv  Detail & Related papers  (2022-04-27T10:38:33Z)
• Square Root Bundle Adjustment for Large-Scale Reconstruction [56.44094187152862]
  We propose a new formulation for the bundle adjustment problem which relies on nullspace marginalization of landmark variables by QR decomposition. Our approach, which we call square root bundle adjustment, is algebraically equivalent to the commonly used Schur complement trick. We show in real-world experiments with the BAL datasets that even in single precision the proposed solver achieves on average equally accurate solutions.
  arXiv  Detail & Related papers  (2021-03-02T16:26:20Z)
• On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent [55.96478231566129]
  We show that relative scales play an important role in determining the learned model. We develop a technique for deriving the inductive bias of gradient-flow.
  arXiv  Detail & Related papers  (2021-02-19T07:10:48Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• Boosting Data Reduction for the Maximum Weight Independent Set Problem Using Increasing Transformations [59.84561168501493]
  We introduce new generalized data reduction and transformation rules for the maximum weight independent set problem. Surprisingly, these so-called increasing transformations can simplify the problem and also open up the reduction space to yield even smaller irreducible graphs later in the algorithm. Our algorithm computes significantly smaller irreducible graphs on all except one instance, solves more instances to optimality than previously possible, is up to two orders of magnitude faster than the best state-of-the-art solver, and finds higher-quality solutions than solvers DynWVC and HILS.
  arXiv  Detail & Related papers  (2020-08-12T08:52:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.