We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse-to-fine fashion.
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.
Our flow-to-depth layer is differentiable, and thus we can refine camera poses by maximizing the aggregated confidence in the camera pose refinement module.
The explicit constraints on both depth (structure) and pose (motion), when combined with the learning components, bring the merit from both traditional BA and emerging deep learning technology.
The input to the network is the raw point cloud of a scene and the output are image or image sequences from a novel view or along a novel camera trajectory.
In contrast, we propose adaptive thin volumes (ATVs); in an ATV, the depth hypothesis of each plane is spatially varying, which adapts to the uncertainties of previous per-pixel depth predictions.
Ranked #13 on 3D Reconstruction on DTU
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.
Many real-world video sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation on video sequences would lead to difficulty.
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research.
Ranked #1 on 3D Reconstruction on 300W
The first is trained to synthesize a diverse set of plausible segmentations that conform to the user's input.
Ranked #10 on Interactive Segmentation on SBD
Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty.
Ranked #1 on Motion Segmentation on KT3DMoSeg
We propose an end-to-end deep learning architecture that produces a 3D shape in triangular mesh from a single color image.
Ranked #3 on 3D Object Reconstruction on Data3D−R2N2 (Avg F1 metric)
We present a method to jointly estimate scene depth and recover the clear latent image from a foggy video sequence.