3D Semantic Scene Completion
25 papers with code • 4 benchmarks • 5 datasets
This task was introduced in "Semantic Scene Completion from a Single Depth Image" (https://arxiv.org/abs/1611.08974) at CVPR 2017 . The target is to infer the dense 3D voxelized semantic scene from an incompleted 3D input (e.g. point cloud, depth map) and an optional RGB image. A recent summary can be found in the paper "3D Semantic Scene Completion: a Survey" (https://arxiv.org/abs/2103.07466), published at IJCV 2021.
NYUv2
SemanticKITTI
KITTI-360
PRO-teXt
SSCBench
Most implemented papers
Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
yjcaimeow/SISNet
•
•
CVPR 2021
The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the overall scene.
Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds
Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information.
ATISS: Autoregressive Transformers for Indoor Scene Synthesis
nv-tlabs/atiss
•
•
NeurIPS 2021
The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis for training and simulation.
Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
UnBVision/spawn
•
•
In this paper, we introduce the use of a 3D data augmentation strategy that can be applied to multimodal SSC networks.
MonoScene: Monocular 3D Semantic Scene Completion
cv-rits/MonoScene
•
•
CVPR 2022
MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image.
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
nvlabs/voxformer
•
•
CVPR 2023
To enable such capability in AI systems, we propose VoxFormer, a Transformer-based semantic scene completion framework that can output complete 3D volumetric semantics from only 2D images.
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems.
SCPNet: Semantic Scene Completion on Point Cloud
SCPNet/Codes-for-SCPNet
•
•
CVPR 2023
We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects.
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
However, due to the inherent representation gap between stereo geometry and BEV features, it is non-trivial to bridge them for dense prediction task of SSC.
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
zhangyp15/occformer
•
•
ICCV 2023
The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy.
