SOTAVerified

Point cloud reconstruction

This task aims to solve inherent problems in raw point clouds: sparsity, noise, and irregularity.

Papers

Showing 125 of 101 papers

TitleStatusHype
VGGT: Visual Geometry Grounded TransformerCode11
fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial IntelligenceCode4
Curve-Aware Gaussian Splatting for 3D Parametric Curve ReconstructionCode2
DSRC: Learning Density-insensitive and Semantic-aware Collaborative Representation against CorruptionsCode1
Unsupervised Occupancy Learning from Sparse Point CloudCode1
DiffPMAE: Diffusion Masked Autoencoders for Point Cloud ReconstructionCode1
Lightweight super resolution network for point cloud geometry compressionCode1
Variational Autoencoding of Dental Point CloudsCode1
PAPR: Proximity Attention Point RenderingCode1
APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud ReconstructionCode1
Energy-Based Sliced Wasserstein DistanceCode1
Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose EstimationCode1
Sparse2Dense: Learning to Densify 3D Features for 3D Object DetectionCode1
Cross-modal Learning for Image-Guided Point Cloud Shape CompletionCode1
Masked Surfel Prediction for Self-Supervised Point Cloud LearningCode1
Masked Autoencoders in 3D Point Cloud Representation LearningCode1
Autoregressive 3D Shape Generation via Canonical MappingCode1
Local and Global Point Cloud Reconstruction for 3D Hand Pose EstimationCode1
PointMixer: MLP-Mixer for Point Cloud UnderstandingCode1
Patch-Based Deep Autoencoder for Point Cloud Geometry CompressionCode1
3D Surface Reconstruction From Multi-Date Satellite ImagesCode1
Canonical Capsules: Self-Supervised Capsules in Canonical PoseCode1
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency CheckingCode1
From Image Collections to Point Clouds with Self-supervised Shape and Pose NetworksCode1
M^3VSNet: Unsupervised Multi-metric Multi-view Stereo NetworkCode1
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.