OpenCodePapers

3d-semantic-scene-completion-from-a-single-1

Single-View 3D Reconstruction3D Semantic Scene Completion from a single RGB image
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemIoUModelNameReleaseDate
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion✓ Link16.63CGFormer2024-05-22
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries✓ Link15.04Symphonies2023-06-27
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space✓ Link12.58NDC-Scene2023-09-26
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction✓ Link12.32OccFormer2023-04-11
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion✓ Link12.20VoxFormer2023-02-23
MonoScene: Monocular 3D Semantic Scene Completion✓ Link11.08MonoScene2021-12-01
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion✓ Link8.97JS3C-Net (rgb input - reported in MonoScene paper)2020-12-07
LMSCNet: Lightweight Multiscale 3D Semantic Completion✓ Link7.09LMSCNet (rgb input - reported in MonoScene paper)2020-08-24
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior✓ Link6.233DSketch (rgb input - reported in MonoScene paper)2020-03-31