3D Semantic Scene Completion from a single RGB image 벤치마크

3D Semantic Scene Completion from a single RGB image on SemanticKITTI

54개 결과 · ⬇ CSV · JSON

mIoU

Rank	Model	mIoU	Paper	Code	Year
1	CGFormer	16.63	Context and Geometry Aware Voxel Transformer for Semantic Scene Completion	pkqbajng/cgformer	2024
2	Symphonies	15.04	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	hustvl/symphonies	2023
3	NDC-Scene	12.58	NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space	Jiawei-Yao0812/NDCScene	2023
4	OccFormer	12.32	OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction	zhangyp15/occformer	2023
5	VoxFormer	12.20	VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion	nvlabs/voxformer	2023
6	MonoScene	11.08	MonoScene: Monocular 3D Semantic Scene Completion	astra-vision/monoscene · cv-rits/MonoScene	2021
7	JS3C-Net (rgb input - reported in MonoScene paper)	8.97	Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion	yanx27/JS3C-Net · umich-curly/3dmapping	2020
8	LMSCNet (rgb input - reported in MonoScene paper)	7.09	LMSCNet: Lightweight Multiscale 3D Semantic Completion	astra-vision/lmscnet · cv-rits/LMSCNet · umich-curly/3dmapping	2020
9	3DSketch (rgb input - reported in MonoScene paper)	6.23	3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior	charlesCXK/3D-SketchAware-SSC · charlesCXK/TorchSSC	2020
10	CGFormer	16.63	Context and Geometry Aware Voxel Transformer for Semantic Scene Completion	pkqbajng/cgformer	2024
11	Symphonies	15.04	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	hustvl/symphonies	2023
12	NDC-Scene	12.58	NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space	Jiawei-Yao0812/NDCScene	2023
13	OccFormer	12.32	OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction	zhangyp15/occformer	2023
14	VoxFormer	12.20	VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion	nvlabs/voxformer	2023
15	MonoScene	11.08	MonoScene: Monocular 3D Semantic Scene Completion	astra-vision/monoscene · cv-rits/MonoScene	2021
16	JS3C-Net (rgb input - reported in MonoScene paper)	8.97	Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion	yanx27/JS3C-Net · umich-curly/3dmapping	2020
17	LMSCNet (rgb input - reported in MonoScene paper)	7.09	LMSCNet: Lightweight Multiscale 3D Semantic Completion	astra-vision/lmscnet · cv-rits/LMSCNet · umich-curly/3dmapping	2020
18	3DSketch (rgb input - reported in MonoScene paper)	6.23	3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior	charlesCXK/3D-SketchAware-SSC · charlesCXK/TorchSSC	2020
19	CGFormer	16.63	Context and Geometry Aware Voxel Transformer for Semantic Scene Completion	pkqbajng/cgformer	2024
20	Symphonies	15.04	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	hustvl/symphonies	2023