We propose Neural Gradient Learning (NGL), a deep learning approach to l...
Learning implicit representations has been a widely used solution for su...
Latest methods represent shapes with open surfaces using unsigned distan...
Learning signed distance functions (SDFs) from 3D point clouds is an
imp...
Neural signed distance functions (SDFs) have shown remarkable capability...
We propose a novel method called SHS-Net for oriented normal estimation ...
Learning and selecting important points on a point cloud is crucial for ...
In this paper, we present a new method for the multiview registration of...
It is vital to infer signed distance functions (SDFs) from 3D point clou...
Normal estimation for unstructured point clouds is an important task in ...
We propose a novel normal estimation method called HSurf-Net, which can
...
Surface reconstruction for point clouds is an important task in 3D compu...
Learning radiance fields has shown remarkable results for novel view
syn...
Deep implicit functions have shown remarkable shape modeling ability in
...
Surface reconstruction from point clouds is vital for 3D computer vision...
It is an important task to reconstruct surfaces from 3D point clouds. Cu...
Reconstructing 3D shape from a single 2D image is a challenging task, wh...
Learning representations for point clouds is an important task in 3D com...
Deep Implicit Function (DIF) has gained popularity as an efficient 3D sh...
Point cloud completion concerns to predict missing part for incomplete 3...
Most existing point cloud completion methods suffered from discrete natu...
As real-scanned point clouds are mostly partial due to occlusions and
vi...
Unpaired 3D object completion aims to predict a complete 3D shape from a...
Point cloud completion aims to predict a complete shape in high accuracy...
Learning to generate 3D point clouds without 3D supervision is an import...
Unsupervised learning of global features for 3D shape analysis is an
imp...
In this paper, we present a novel unpaired point cloud completion networ...
The task of point cloud upsampling aims to acquire dense and uniform poi...
The task of point cloud completion aims to predict the missing part for ...
Reconstructing continuous surfaces from 3D point clouds is a fundamental...
Differentiable renderers have been used successfully for unsupervised 3D...
Fine-grained 3D shape classification is important and research challengi...
Point cloud completion aims to infer the complete geometries for missing...
Learning discriminative feature directly on point clouds is still challe...
Learning discriminative feature directly on point clouds is still challe...
Structure learning for 3D shapes is vital for 3D computer vision.
State-...
Model View Definition (MVD) is the standard methodology to define the
ex...
Model View Definition (MVD) is the standard methodology to define the pa...
Low-rank metric learning aims to learn better discrimination of data sub...
Learning discriminative shape representation directly on point clouds is...
Auto-encoder is an important architecture to understand point clouds in ...
3D shape captioning is a challenging application in 3D shape understandi...
Unsupervised feature learning for point clouds has been vital for large-...
Deep learning has achieved remarkable results in 3D shape analysis by
le...
Learning global features by aggregating information over multiple views ...
Cross-modal retrieval aims to retrieve relevant data across different
mo...
A recent method employs 3D voxels to represent 3D shapes, but this limit...
In this paper we present a novel unsupervised representation learning
ap...
Exploring contextual information in the local region is important for sh...