Zobrazeno 1 - 10
of 269
pro vyhledávání: '"Han, Zhizhong"'
Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy function. However,
Externí odkaz:
http://arxiv.org/abs/2404.06851
Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patches, upsampl
Externí odkaz:
http://arxiv.org/abs/2312.15133
Cross-modality registration between 2D images from cameras and 3D point clouds from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D-3D correspondences by matching point and pixel patterns learned by neural networ
Externí odkaz:
http://arxiv.org/abs/2312.04060
Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing. The state-of-the-art methods rely on priors of fitting local surfaces learned from normal supervision. However, normal supervision in benchmarks comes from synthet
Externí odkaz:
http://arxiv.org/abs/2311.00389
Autor:
Hu, Pengchong, Han, Zhizhong
Learning neural implicit representations has achieved remarkable performance in 3D reconstruction from multi-view images. Current methods use volume rendering to render implicit representations into either RGB or depth images that are supervised by m
Externí odkaz:
http://arxiv.org/abs/2310.11598
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. It has excellent gradient approximation properties for the underlying geometry of th
Externí odkaz:
http://arxiv.org/abs/2309.09211
Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point cloud. However, these methods
Externí odkaz:
http://arxiv.org/abs/2308.13175
Latest methods represent shapes with open surfaces using unsigned distance functions (UDFs). They train neural networks to learn UDFs and reconstruct surfaces with the gradients around the zero level set of the UDF. However, the differential networks
Externí odkaz:
http://arxiv.org/abs/2308.11441
In recent years, huge progress has been made on learning neural implicit representations from multi-view images for 3D reconstruction. As an additional input complementing coordinates, using sinusoidal functions as positional encodings plays a key ro
Externí odkaz:
http://arxiv.org/abs/2308.11025
Learning per-point semantic features from the hierarchical feature pyramid is essential for point cloud semantic segmentation. However, most previous methods suffered from ambiguous region features or failed to refine per-point features effectively,
Externí odkaz:
http://arxiv.org/abs/2308.09314