5 citations · 5 across the 6 of their papers we have counts for
7 papers
FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow
Sadra Safadoust, Fabio Tosi, Matteo Poggi +1
We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a h…
WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields
Sadra Safadoust, Fabio Tosi, Fatma Güney +1
We introduce WarpRF, a training-free general-purpose framework for quantifying the uncertainty of radiance fields. Built upon the assumption that photometric and geometric consiste…
Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs
Sadra Safadoust, Fabio Tosi, Fatma Güney +1
3D Gaussian Splatting (GS) significantly struggles to accurately represent the underlying 3D scene geometry, resulting in inaccuracies and floating artifacts when rendering depth m…
Multi-Object Discovery by Low-Dimensional Object Motion
Sadra Safadoust, Fatma Güney
Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without…
DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax
Sadra Safadoust, Fatma Güney
Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known s…
Stochastic Video Prediction with Structure and Motion
Adil Kaan Akan, Sadra Safadoust, Fatma Güney
While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot p…
Self-Supervised Monocular Scene Decomposition and Depth Estimation
Sadra Safadoust, Fatma Güney
Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose Mono…