SOTAVerified

3D Semantic Scene Completion

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 65 papers

TitleStatusHype
Tri-Perspective View for Vision-Based 3D Semantic Occupancy PredictionCode3
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene CompletionCode3
OccDepth: A Depth-Aware Method for 3D Semantic Scene CompletionCode2
SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous DrivingCode2
Hierarchical Temporal Context Learning for Camera-based Semantic Scene CompletionCode2
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy PredictionCode2
Disentangling Instance and Scene Contexts for 3D Semantic Scene CompletionCode1
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure PriorCode1
Anisotropic Convolutional Networks for 3D Semantic Scene CompletionCode1
ATISS: Autoregressive Transformers for Indoor Scene SynthesisCode1
Camera-based 3D Semantic Scene Completion with Sparse Guidance NetworkCode1
2D Semantic-Guided Semantic Scene CompletionCode1
LMSCNet: Lightweight Multiscale 3D Semantic CompletionCode1
MonoScene: Monocular 3D Semantic Scene CompletionCode1
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates SpaceCode1
Offboard Occupancy Refinement with Hybrid Propagation for Autonomous DrivingCode1
SCPNet: Semantic Scene Completion on Point CloudCode1
Semantic Scene Completion via Integrating Instances and Scene in-the-LoopCode1
Semantic Segmentation-assisted Scene Completion for LiDAR Point CloudsCode1
SGFormer: Satellite-Ground Fusion for 3D Semantic Scene CompletionCode1
Skip Mamba Diffusion for Monocular 3D Semantic Scene CompletionCode1
SOAP: Vision-Centric 3D Semantic Scene Completion with Scene-Adaptive Decoder and Occluded Region-Aware View ProjectionCode1
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene CompletionCode1
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene CompletionCode1
Symphonize 3D Semantic Scene Completion with Contextual Instance QueriesCode1
TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of SightCode1
VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene CompletionCode1
SCFusion: Real-time Incremental Scene Reconstruction with Semantic CompletionCode0
Data Augmented 3D Semantic Scene Completion with 2D Segmentation PriorsCode0
See and Think: Disentangling Semantic Scene CompletionCode0
Semantic Scene Completion from a Single Depth ImageCode0
EdgeNet: Semantic Scene Completion from a Single RGB-D ImageCode0
Efficient Semantic Scene Completion Network with Spatial Group ConvolutionCode0
Camera-Only 3D Panoptic Scene Completion for Autonomous Driving through Differentiable Object ShapesCode0
Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction—0
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion—0
S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds—0
Scene Synthesis from Human Motion—0
Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations—0
Semantic Point Completion Network for 3D Semantic Scene Completion—0
Semantic Scene Completion Combining Colour and Depth: preliminary experiments—0
Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data—0
3D GANs and Latent Space: A comprehensive survey—0
Towards 3D Semantic Scene Completion for Autonomous Driving: A Meta-Learning Framework Empowered by Deformable Large-Kernel Attention and Mamba Model—0
Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance—0
Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion—0
3D Gated Recurrent Fusion for Semantic Scene Completion—0
Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion—0
DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation—0
Two Stream 3D Semantic Scene Completion—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsNYUv2SemanticKITTIKITTI-360PRO-teXt

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SG-SSCmIoU55.4—Unverified
2SISNetmIoU52.4—Unverified
3SPAwN (SUNCG pretraining)mIoU49.9—Unverified
4SPAwNmIoU48—Unverified
5Point-Voxel Aggregation NetworkmIoU46—Unverified
6CCPNet (SUNCG pretraining)mIoU41.3—Unverified
73DSketchmIoU41.1—Unverified
8ForkNet (SUNCG pretraining)mIoU37.1—Unverified
9IPF-SPCNet: Semantic point completion network for 3D semantic scene completionmIoU35.1—Unverified
10Real-time semantic scene completion via feature aggregation and conditioned predictionmIoU34.4—Unverified
#ModelMetricClaimedVerifiedStatus
1TALoSmIoU37.9—Unverified
2SCPNetmIoU36.7—Unverified
3S3CNetmIoU29.5—Unverified
4JS3C-NetmIoU23.8—Unverified
5SSA-SCmIoU23.5—Unverified
6Local-DIFsmIoU22.7—Unverified
7UDNetmIoU19.5—Unverified
8TS3D+DNet+SATNet (Reported in SemanticKITTI dataset paper)mIoU17.7—Unverified
9LMSCNet-SSmIoU17.6—Unverified
10ESSCNetmIoU17.5—Unverified
#ModelMetricClaimedVerifiedStatus
1SymphoniesmIoU18.58—Unverified
2SSCNetmIoU16.95—Unverified
3OccFormermIoU13.81—Unverified
4LMSCNetmIoU13.65—Unverified
5TPVFormermIoU13.64—Unverified
6MonoScenemIoU12.31—Unverified
7VoxFormermIoU11.91—Unverified
#ModelMetricClaimedVerifiedStatus
1LSDMF10.52—Unverified
2MIMEF10.1—Unverified
3SUMMONF10.07—Unverified
4ATISSF10.07—Unverified