Papers
arxiv:2405.02296

Möbius Transform for Mitigating Perspective Distortions in Representation Learning

Published on Mar 7, 2024
Authors:
,
,
,
,

Abstract

A method employs M\"obius transform for mitigating perspective distortion in images without camera parameter estimation, outperforming existing benchmarks in various computer vision tasks.

Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task that prevents synthesizing perspective distortion. Non-availability of dedicated training data poses a critical barrier to developing robust computer vision methods. Additionally, distortion correction methods make other computer vision tasks a multi-step approach and lack performance. In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of M\"obius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data. Also, we present a dedicated perspectively distorted benchmark dataset, ImageNet-PD, to benchmark the robustness of deep learning models against this new dataset. The proposed method outperforms existing benchmarks, ImageNet-E and ImageNet-X. Additionally, it significantly improves performance on ImageNet-PD while consistently performing on standard data distribution. Notably, our method shows improved performance on three PD-affected real-world applications crowd counting, fisheye image recognition, and person re-identification and one PD-affected challenging CV task: object detection. The source code, dataset, and models are available on the project webpage at https://prakashchhipa.github.io/projects/mpd.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2405.02296
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 2

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2405.02296 in a Space README.md to link it from this page.

Collections including this paper 1