Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation

1 code implementation • 10 Dec 2022 • Lior Talker, Aviad Cohen, Erez Yosef, Alexandra Dana, Michael Dinerstein

To the best of our knowledge this paper is the first attempt to address the depth edges issue for LIDAR-supervised scenes.

Monocular Depth Estimation Novel View Synthesis

Consistent Semantic Attacks on Optical Flow

no code implementations • 16 Nov 2021 • Tom Koren, Lior Talker, Michael Dinerstein, Roy J Jevnisek

We present a novel approach for semantically targeted adversarial attacks on Optical Flow.

Optical Flow Estimation

Efficient Sliding Window Computation for NN-Based Template Matching

no code implementations • ECCV 2018 • Lior Talker, Yael Moses, Ilan Shimshoni

The main contribution of our method is an algorithm for incrementally computing the score of each image window based on the score computed for the previous window.

Template Matching

Using Spatial Order to Boost the Elimination of Incorrect Feature Matches

no code implementations • CVPR 2016 • Lior Talker, Yael Moses, Ilan Shimshoni

To this end, we propose to analyze the set of matches using the spatial order of the features, as projected to the x-axis of the image.

Have a Look at What I See

no code implementations • 19 May 2015 • Lior Talker, Yael Moses, Ilan Shimshoni

These images may be available online from other photographers who are present at the scene.

3D Scene Reconstruction