SOTAVerified

3D Semantic Scene Completion from a single RGB image

This task relies on a single RGB image to infer the dense 3D voxelized semantic scene.

Papers

Showing 110 of 11 papers

TitleStatusHype
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene CompletionCode3
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy PredictionCode2
Context and Geometry Aware Voxel Transformer for Semantic Scene CompletionCode2
Monocular Occupancy Prediction for Scalable Indoor ScenesCode2
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates SpaceCode1
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene CompletionCode1
Symphonize 3D Semantic Scene Completion with Contextual Instance QueriesCode1
MonoScene: Monocular 3D Semantic Scene CompletionCode1
Anisotropic Convolutional Networks for 3D Semantic Scene CompletionCode1
LMSCNet: Lightweight Multiscale 3D Semantic CompletionCode1
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.