Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Computer Vision and Image Understanding

Hoàng-Ân Lê Tushar Nimbhorkar Thomas Mensink A. S. Baslamisli Sezer Karaoglu Theo Gevers Nikos Paragios
· 0 citations · 32 references

TL;DR

Extensive experimental results show that training on the automatically generated optical flow outperforms methods that are trained on rigid synthetic data using FlowNet-S, LiteFlowNet, PWC-Net, PWC-Net, and RAFT.

Semantic Scholar
View source

Similar papers

Aug 2026

Digging Into Monocular Texture-Scale Feature Fusion for Optical Flow and Optical Expansion Estimation

Visual perception in dynamic scenes is a crucial task in the fields of computer vision and autonomous driving. In this paper, we focus on monocular optical flow and expansion estimation. Optical flow describes the positional changes of pixels between two frames, while optical expansion describes local image-scale chang...

Chang-Lin Li, Ye-Qiang Qian, Chun-Xiang Wang et al. · 0 citations
Sep 2026

MonoSOWA++: Universal Autolabeling Pipeline for Monocular 3D Object Detection

A method to train a 3D object detector from a single RGB camera without domain-specific human annotations, making orders of magnitude more data available for training and shows that combining pseudo-labels from multiple datasets can achieve comparable accuracy to using human labels from a single dataset.

Jan Skvrna, Lukás Neumann · 0 citations

Computer Vision and Image Understanding

This work proposes albedo and shading gradient descriptors which are derived from physics-based models and is the first to directly address the texture and intensity ambiguity problems of the shading estimations.

A. S. Baslamisli, Yang Liu, Sezer Karaoglu et al. · 0 citations
Preprint Sep 2026

Data-Efficient Crosswalk Segmentation from Overhead CCTV via Confidence- and Geometry-Guided Pseudo-Labeling

Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabel...

Abdirashid A. Omar, Jonghyuk Park · 0 citations
Preprint Oct 2026

4Director: Controlling Video World Models with Rigid 3D Geometry

Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We int...

Wei Cao, Hao Zhang, Vikram Voleti et al. · 1 citation
May 2025

Object Concepts Emerge from Motion

A biologically inspired framework for learning object-centric visual representations in an unsupervised manner, suggesting that motion-induced object representations offer a compelling alternative to existing vision foundation models, capturing a crucial but overlooked level of abstraction: the visual instance.

Hao Liang, Xiao-Hui Wang, Zhi-Chao Li et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.