… disparity maps of medium accuracy, we focus on designing a Neural Disparity Refinement
… by the fact that our neural network is specifically trained to refine disparity maps within the …

… We introduce a novel architecture for neural disparity re… that enables to estimate a refined
disparity map at any arbitrary output … Moreover, our neural network can process seamlessly the …

… Moreover, neural implicit representations have been enhanced towards interactive RGB-D …
quality of methods utilizing implicit neural representations is significantly lower than for …

… Disparity Generation’, we study the effect of the disparity … the search process with hypothesis
disparities, and K controls the … Epi-patch based convolutional neural network for depth …

… stages gives the final disparity. As opposed to directly learning the disparity at the second
stage… computation, cost aggregation, disparity optimization, to disparity refinement by a stack of …

… We refine the matching cost by enforcing smoothness constraints on the disparity image.
Following Hirschmuller [4], we define an energy function E(D) that depends on the …

… Stereo matching has first been solved using model-based approaches, with real-time
considerations for some, but today’s most recent works rely on deep convolutional neural networks …

… our method to refine the initial disparity map. … neural method can be applied to achieve
accurate disparity map. After training, the BP network is first used to generate an initial disparity …

… With disparity patches as the input, convolutional neural … confidence map using a deep
neural network based on learned … for disparity refinement: We compute the refined disparity map …

… a disparity refinement method that directly refines the winner-take-all (WTA) disparity map by
… is over-segmented into superpixels and a disparity plane is fitted for each superpixel by an …