Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction
Not on the map. Why?
Abstract (arXiv)
Semantic Scene Completion (SSC) aims to simultaneously predict the volumetric occupancy and semantic category of a 3D scene. In this paper, we propose a real-time semantic scene completion method with a feature aggregation strategy and conditioned prediction module. Feature aggregation fuses feature with different receptive fields and gathers context to improve scene completion performance. And the conditioned prediction module adopts a two-step prediction scheme that takes volumetric occupancy as a condition to enhance semantic completion prediction. We conduct experiments on three recognized benchmarks NYU, NYUCAD, and SUNCG. Our method achieves competitive performance at a speed of 110 FPS on one GTX 1080 Ti GPU.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 20 Mar 2023.
Builds on
29 of 39 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
- 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
- 2016Semantic Scene Completion from a Single Depth Imagecited by 468
- 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
- 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
- 2021Conditional DETR for Fast Training Convergencecited by 422
- 2018PCN: Point Completion Networkcited by 382
- 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
- 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 124
17 more
- 2020Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentationcited by 120
- 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
- 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
- 2022Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decompositioncited by 81
- 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
- 2019RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completioncited by 54
- 2018Two Stream 3D Semantic Scene Completioncited by 48
- 2021Joint Implicit Image Function for Guided Depth Super-Resolutioncited by 31
- 2022MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentationcited by 29
- 2018View-volume Network for Semantic Scene Completion from a Single Depth Imagecited by 26
- 2022Group DETR v2: Strong Object Detector with Encoder-Decoder Pretrainingcited by 25
- 2022CAE v2: Context Autoencoder with CLIP Targetcited by 25
- 2021Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspectivecited by 22
- 2022Conditional DETR V2: Efficient Detection Transformer with Box Queriescited by 21
- 2022Point Scene Understanding via Disentangled Instance Mesh Reconstructioncited by 20
- 2022D3ETR: Decoder Distillation for Detection Transformercited by 17
- 2021Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarizationcited by 6
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.
- 2024Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function25 Mar 2024
- 2023Interactive Segment Anything NeRF with Feature Imitation25 May 2023
- 2023Uncovering and Quantifying Social Biases in Code Generation24 May 2023