A Differential Invariant for Zooming
Andreas Siebert
Abstract
This paper presents an invariant under scaling and linear brightness change. The invariant is based on differentials and therefore is a local feature. Rotationally invariant 2-d differential Gaussian operators up to third order are proposed for the implementation of the invariant. The performance is analyzed by simulating a camera zoom-out.
Create a lesson
Related papers
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
Xudong Cai, Ruijie Zhu, Haoliang Shang et al.
InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
Xuanlang Dai, Jiazi Bu, Yujie Zhou et al.
Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback
Yucheng Yang, Xiaoxiao Sun, Shusheng Yang et al.
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Bhanu Tokas, Rahul Nair, Rockwell Jackson et al.
Can machines reason non-verbally?
Shaheer U. Saeed, Zion Tse, Gregory Slabaugh et al.
Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
Junkai Liu, Le Zhang