3D Semantic Scene Completion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 4
- 보존된 평가 기록
- 59
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Jiawei-Yao0812/NDCScene
공식 코드NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space
https://github.com/ShunChengWu/SCFusion/blob/main/README.md
공식 코드SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
https://github.com/ai4ce/sscbench
공식 코드SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
https://github.com/arlo0o/htcl
공식 코드Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion
https://github.com/blue-531/talos
공식 코드TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
https://github.com/cv-rits/LMSCNet
공식 코드https://github.com/cv-rits/MonoScene
공식 코드https://github.com/enyu-liu/disc
공식 코드Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion
https://github.com/gxytcrc/sgformer
공식 코드SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion
https://github.com/hongxiaoy/ISO
공식 코드https://github.com/hustvl/symphonies
공식 코드Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
https://github.com/jieqianyu/sgn
공식 코드Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
https://github.com/jokester-zzz/ssa-sc
공식 코드Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds
https://github.com/masterhow/occfiner
공식 코드Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
https://github.com/megvii-research/occdepth
공식 코드OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
https://github.com/nicolamarinello/offsetocc
공식 코드Camera-Only 3D Panoptic Scene Completion for Autonomous Driving through Differentiable Object Shapes
https://github.com/nv-tlabs/atiss
공식 코드ATISS: Autoregressive Transformers for Indoor Scene Synthesis
https://github.com/nvlabs/voxformer
공식 코드VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
https://github.com/pkqbajng/cgformer
공식 코드Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
https://github.com/shurans/sscnet
공식 코드https://github.com/waterljwant/SSC
공식 코드Anisotropic Convolutional Networks for 3D Semantic Scene Completion
https://github.com/willemeng/VLScene
공식 코드VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion
https://github.com/wzzheng/tpvformer
공식 코드Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
https://github.com/xrkong/skimba
공식 코드Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion
https://github.com/yanx27/JS3C-Net
공식 코드https://github.com/yjcaimeow/SISNet
공식 코드Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
https://github.com/zhangyp15/occformer
공식 코드OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
https://github.com/zjhthu/SGC-Release
공식 코드Efficient Semantic Scene Completion Network with Spatial Group Convolution
https://gitlab.com/UnBVision/edgenet
공식 코드EdgeNet: Semantic Scene Completion from a Single RGB-D Image
https://gitlab.com/UnBVision/spawn
공식 코드Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
https://github.com/SCPNet/Codes-for-SCPNet
https://github.com/ShunChengWu/SCFusion_Network
SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
https://github.com/aipixel/SG-SSC
https://github.com/astra-vision/lmscnet
https://github.com/astra-vision/monoscene
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.