paper-with-me

Papers

Learning a Depth Covariance Function

2023-03-21 · CVPR 2023 1 · Eric Dexheimer, Andrew J. Davison

We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.

📄 PDF Abstract BibTeX arXiv:2303.12157

Code (0)

등록된 구현이 없습니다.

Tasks

Depth CompletionVisual Odometry

Similar Papers 제목 키워드 기반

The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization

2022-06-06 · Mufan Bill Li, Mihai Nica, Daniel M. Roy

The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, given a random covariance matrix defined by the penultimate layer. In this work, we study the distribution of this random ma…

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

2023-03-31 · CVPR 2023 6 · Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte 외

Neural-network-based single image depth prediction (SIDP) is a challenging task where the goal is to predict the scene's per-pixel depth at test time. Since the problem, by definition, is ill-posed, the fundamental goal …

Depth EstimationDepth Prediction

COMO: Compact Mapping and Odometry

2024-04-04 · Eric Dexheimer, Andrew J. Davison

We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via per-keyframe depth covarianc…

Commutative Width and Depth Scaling in Deep Neural Networks

2023-10-02 · Soufiane Hayou

This paper is the second in the series Commutative Scaling of Width and Depth (WD) about commutativity of infinite width and depth limits in deep neural networks. Our aim is to understand the behaviour of neural function…

Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time

2025-10-01 · Blake Bordelon, Mary I. Letey, Cengiz Pehlevan arxiv

We study in-context learning (ICL) of linear regression in a deep linear self-attention model, characterizing how performance depends on various computational and statistical resources (width, depth, number of training s…