We propose an online multi-view depth prediction approach on posed video streams, where the scene geometry information computed in the previous time steps is propagated to the current time step in an efficient and geometrically plausible way.
We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo.
Ranked #5 on Point Clouds on Tanks and Temples
Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation.
Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze.
We show, for the first time, how to jointly reconstruct both the individual tracer particles and a dense 3D fluid motion field from the image data, using an integrated energy minimization.
We propose a new method for iterative particle reconstruction (IPR), in which the locations and intensities of all particles are inferred in one joint energy minimization.
We propose a novel framework for the discretisation of multi-label problems on arbitrary, continuous domains.
We propose an adaptive multi-resolution formulation of semantic 3D reconstruction.