paper-with-me

홈 › Papers

SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries

2024-09-23 · Sebastian Janampa, Marios Pattichis

Camera calibration consists of estimating camera parameters such as the zenith vanishing point and horizon line. Estimating the camera parameters allows other tasks like 3D rendering, artificial reality effects, and object insertion in an image. Transformer-based models have provided promising results; however, they lack cross-scale interaction. In this work, we introduce \textit{multi-Scale defOrmable transFormer for camera calibratIon with enhanced line queries}, SOFI. SOFI improves the line queries used in CTRL-C and MSCC by using both line content and line geometric features. Moreover, SOFI's line queries allow transformer models to adopt the multi-scale deformable attention mechanism to promote cross-scale interaction between the feature maps produced by the backbone. SOFI outperforms existing methods on the \textit {Google Street View}, \textit {Horizon Line in the Wild}, and \textit {Holicity} datasets while keeping a competitive inference speed.

📄 PDF Abstract BibTeX arXiv:2409.15553

Code (1)

sebastianjanampa/sofi 공식 구현 pytorch

Tasks

Camera Calibration

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Parallel Statistical Multi-resolution Estimation

2015-03-10 · Jan Lebert, Lutz Künneke, Johannes Hagemann, Stephan C. Kramer

We discuss several strategies to implement Dykstra's projection algorithm on NVIDIA's compute unified device architecture (CUDA). Dykstra's algorithm is the central step in and the computationally most expensive part of …

CPUSuper-Resolution

BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs

2022-03-08 · Lang Peng, Zhirong Chen, Zhangjie Fu, Pengpeng Liang 외

Semantic segmentation in bird's eye view (BEV) is an important task for autonomous driving. Though this task has attracted a large amount of research efforts, it is still challenging to flexibly cope with arbitrary (sing…

Autonomous DrivingBird's-Eye View Semantic SegmentationDecoderSegmentation+1

ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis

2024-12-19 · Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao 외

Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevalent. However, the quality and utility of …

Data AugmentationSynthetic Data Generation

SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix

2024-03-05 · Mrinmay Sen, A. K. Qin, Gayathri C, Raghu Kishore N 외

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton…

image-classificationImage ClassificationStochastic Optimization

DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix

2026-01-14 · Sidhant Nair, Tanmay Sen, Mrinmay Sen, Sayantan Banerjee arxiv

Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradient quality. Although second-order optim…

Stochastic OptimizationFederated Learning