https://github.com/yahidar/transradar
공식 코드TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation
Papers with Code 아카이브
Scene Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 3
- 보존된 평가 기록
- 5
Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yang-li-2000/distance-aware-occlusion-detection-with-focused-attention
공식 코드https://github.com/yanhaowu/oessl
공식 코드https://github.com/yanx27/clevr3d
공식 코드Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation
https://github.com/yaohungt/GSTEG_CVPR_2019
공식 코드Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
https://github.com/ybarancan/bev_feat_stitch
공식 코드Understanding Bird's-Eye View of Road Semantics using an Onboard Camera
https://github.com/ybarancan/stsu
공식 코드Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images
https://github.com/yhc2021/avs-net
공식 코드AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding
https://github.com/yichen928/STRL
공식 코드Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
https://github.com/yichizhang98/sam4mis
공식 코드Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey
https://github.com/yifanlu0227/chatsim
공식 코드Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents
https://github.com/yikang-li/FactorizableNet
공식 코드Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
https://github.com/yikang-li/MSDN
공식 코드Scene Graph Generation from Objects, Phrases and Region Captions
https://github.com/yinyunie/RfDNet
공식 코드RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
https://github.com/yinyunie/Total3DUnderstanding
공식 코드https://github.com/yjcaimeow/SISNet
공식 코드Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
https://github.com/yk-pku/two-shot-video-object-segmentation
공식 코드https://github.com/ykarmesh/stable-control-representations
공식 코드Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
https://github.com/ykiwu/embodiedocc
공식 코드EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
https://github.com/youjunzhao/openscan
공식 코드OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding
https://github.com/youngfly11/ReIR-WeaklyGrounding.pytorch
공식 코드Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
https://github.com/yoxu515/aot-benchmark
공식 코드Scalable Video Object Segmentation with Identification Mechanism
https://github.com/yoxu515/mits
공식 코드Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
https://github.com/yoxu515/viposeg-benchmark
공식 코드https://github.com/yrcong/NODIS
공식 코드https://github.com/yrcong/sttran
공식 코드Spatial-Temporal Transformer for Dynamic Scene Graph Generation
https://github.com/yucornetto/CAKES
공식 코드CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks
https://github.com/yuhuan-wu/P2T
공식 코드https://github.com/yujun0-0/mma-net
공식 코드VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
https://github.com/yuk6heo/GIS-RAmap
공식 코드Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
https://github.com/yuk6heo/IVOS-ATNet
공식 코드Interactive Video Object Segmentation Using Global and Local Transfer Modules
https://github.com/yuliang-liu/monkey
공식 코드Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models
https://github.com/yun-liu/hat-net
공식 코드https://github.com/yunkezhang/TCVOM
공식 코드https://github.com/yunlong10/ads-1k
공식 코드Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward
https://github.com/yunongLiu1/IKEA-Manuals-at-Work
공식 코드IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.