3D Object Reconstruction From A Single Image
9 papers with code • 2 benchmarks • 2 datasets
Image: Fan et al
Summary: BWA-MEM is a new alignment algorithm for aligning sequence reads or long query sequences against a large reference genome such as human.
Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images.
We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.
Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object.
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image.
We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making use of differentiable point cloud renderer to train with 2D supervision.
Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets.
Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry.