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/jwfangit/gate-dap
공식 코드https://github.com/jyhong0304/visual-relationship-detection-rwfn
공식 코드https://github.com/jzengust/RGBD2Normal
공식 코드Deep Surface Normal Estimation with Hierarchical RGB-D Fusion
https://github.com/k-radlak/IDCNN
공식 코드Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images
https://github.com/kagawa588/gvseg
공식 코드https://github.com/kai422/covos
공식 코드Accelerating Video Object Segmentation with Compressed Video
https://github.com/kailaisun/indoor-depth-completion
공식 코드A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion
https://github.com/kamiLight/CADepth-master
공식 코드Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
https://github.com/kasiv008/OFFSEG
공식 코드OFFSEG: A Semantic Segmentation Framework For Off-Road Driving
https://github.com/kav-institute/imptc-dataset
공식 코드The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset
https://github.com/keeganhk/pointvst
공식 코드https://github.com/kemaloksuz/LRP-Error
공식 코드https://github.com/kfan21/eoras
공식 코드https://github.com/kimsekeun/medivista-sam
공식 코드MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for Echocardiography
https://github.com/kimsunkyung/SCA_MTL
공식 코드https://github.com/kmaag/Temporal-False-Negative-Reduction
공식 코드False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
https://github.com/kshitij3112/evlpsnet
공식 코드https://github.com/kshitij3112/evpsnet
공식 코드https://github.com/kwonjunn01/hi-mapper
공식 코드Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping
https://github.com/kyusik-cho/cmom
공식 코드Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixing
https://github.com/l1997i/DurLAR
공식 코드On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR
https://github.com/lalithjets/domain-adaptation-in-mtl
공식 코드https://github.com/lalithjets/global-reasoned-multi-task-model
공식 코드Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
https://github.com/lancasterli/refsam
공식 코드RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
https://github.com/lanlan96/3drm
공식 코드https://github.com/lanmng/sitvos
공식 코드Siamese Network with Interactive Transformer for Video Object Segmentation
https://github.com/lastbasket/surgtpgs
공식 코드SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting
https://github.com/ldenninger/camcontexti2v
공식 코드https://github.com/ldkong1205/LaserMix
공식 코드Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
https://github.com/ldkong1205/calib3d
공식 코드Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
https://github.com/ldkong1205/openess
공식 코드OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies
https://github.com/lei-wang-github/DeepPS2
공식 코드DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
https://github.com/leipingjie/sam2video
공식 코드https://github.com/leiyaocui/strap
공식 코드STRAP: Structured Object Affordance Segmentation with Point Supervision
https://github.com/lelimite4444/BridgeDepthFlow
공식 코드Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.