Spectral super-resolution meets deep learning: Achievements and challenges
Spectral super-resolution (sSR) is a very important technique to obtain hyperspectral images
from only RGB images, which can effectively overcome the high acquisition cost and low …
from only RGB images, which can effectively overcome the high acquisition cost and low …
A Survey of Non‐Rigid 3D Registration
Non‐rigid registration computes an alignment between a source surface with a target
surface in a non‐rigid manner. In the past decade, with the advances in 3D sensing …
surface in a non‐rigid manner. In the past decade, with the advances in 3D sensing …
Meshgpt: Generating triangle meshes with decoder-only transformers
We introduce MeshGPT a new approach for generating triangle meshes that reflects the
compactness typical of artist-created meshes in contrast to dense triangle meshes extracted …
compactness typical of artist-created meshes in contrast to dense triangle meshes extracted …
Diffusionnet: Discretization agnostic learning on surfaces
We introduce a new general-purpose approach to deep learning on three-dimensional
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …
Weakly-supervised mesh-convolutional hand reconstruction in the wild
We introduce a simple and effective network architecture for monocular 3D hand pose
estimation consisting of an image encoder followed by a mesh convolutional decoder that is …
estimation consisting of an image encoder followed by a mesh convolutional decoder that is …
Populating 3D scenes by learning human-scene interaction
Humans live within a 3D space and constantly interact with it to perform tasks. Such
interactions involve physical contact between surfaces that is semantically meaningful. Our …
interactions involve physical contact between surfaces that is semantically meaningful. Our …
Primal-dual mesh convolutional neural networks
Recent works in geometric deep learning have introduced neural networks that allow
performing inference tasks on three-dimensional geometric data by defining convolution …
performing inference tasks on three-dimensional geometric data by defining convolution …
Mobrecon: Mobile-friendly hand mesh reconstruction from monocular image
In this work, we propose a framework for single-view hand mesh reconstruction, which can
simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal …
simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal …
Morf: Morphable radiance fields for multiview neural head modeling
Recent research work has developed powerful generative models (eg, StyleGAN2) that can
synthesize complete human head images with impressive photorealism, enabling …
synthesize complete human head images with impressive photorealism, enabling …
Understanding and improving features learned in deep functional maps
S Attaiki, M Ovsjanikov - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Deep functional maps have recently emerged as a successful paradigm for non-rigid 3D
shape correspondence tasks. An essential step in this pipeline consists in learning feature …
shape correspondence tasks. An essential step in this pipeline consists in learning feature …