Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective

arXiv:2404.09051v1 Announce Type: new
Abstract: Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal …

abstract arxiv bridge challenge cs.ai cs.cv diffusion generated however information iteration iterative loss map optimization perspective process rnn type variants