Our #NeurIPS2026 paper on Video Stitching from Multiple Moving Cameras.
Authors: @ShiraIfergane, Roy Amoyal, Shahar Ben Ishay, and Oren Freifeld
Project page: https://t.co/NQgbsk8wWZ
Our #NeurIPS2026 paper “Video Stitching from Multiple Moving Cameras” is now available.
We introduce 𝐭𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐯𝐢𝐝𝐞𝐨 𝐬𝐭𝐢𝐭𝐜𝐡𝐢𝐧𝐠 𝐦𝐞𝐭𝐡𝐨𝐝 that can handle any number of moving cameras.
1/8
7/8 We also introduce a new annotated multi-camera video dataset, with cross-camera and temporal correspondences, and a benchmark for evaluating video stitching methods in this setting.
#NeurIPS2026: 3 papers from our Vision, Inference, and Learning group were accepted. All 3 are related to geometric transformations and deep learning, one of the central research directions in our group.
For more details, see https://t.co/qVh0uosaAq
The 2nd of our 3 #ECCV2024 papers, Trainable Highly-expressive Activation Functions, is now available: https://t.co/5aQhUzwhCq
@shahaffind@irit_chelly Shira Ifergane #deeplearning#computervision
The proposed function, DiTAC, is based on efficient diffeomorphisms (called CPAB).