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/eryixie/planerecnet
공식 코드https://github.com/facebookresearch/ContrastiveSceneContexts
공식 코드Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
https://github.com/facebookresearch/Mask2Former
공식 코드https://github.com/facebookresearch/PointContrast
공식 코드PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
https://github.com/facebookresearch/cutler
공식 코드VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
https://github.com/facebookresearch/edgetam
공식 코드https://github.com/facebookresearch/habitat-api
공식 코드DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
https://github.com/facebookresearch/sam2
공식 코드https://github.com/facebookresearch/uncertainty-driven-active-vision
공식 코드Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
https://github.com/faresbougourzi/ccfg-net
공식 코드Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild
https://github.com/fatemehazimi990/HS2S
공식 코드Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching
https://github.com/fatemehazimi990/RS2S
공식 코드Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory
https://github.com/fedortaggenbrock/self-supervised-partial-cycle-consistency
공식 코드Self-Supervised Partial Cycle-Consistency for Multi-View Matching
https://github.com/feibryantkit/oafuser
공식 코드OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
https://github.com/feipanir/moda
공식 코드https://github.com/fengjiang5/knowledge-distillation-from-cylinder3d-to-polarnet
공식 코드Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation
https://github.com/fengzicai/awesomewmad
공식 코드https://github.com/fengzicai/s2s
공식 코드Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data
https://github.com/fengzicai/wmad-benchmarks
공식 코드https://github.com/fjq-tongji/mllm-sul
공식 코드https://github.com/fnzhan/Illumination-Estimation
공식 코드GMLight: Lighting Estimation via Geometric Distribution Approximation
https://github.com/foundationvision/uniref
공식 코드UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
https://github.com/fpv-iplab/mid-level-fusion-nav
공식 코드https://github.com/franciszzj/HiLo
공식 코드HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation
https://github.com/fraunhoferhhi/soloplanes
공식 코드Multi-task Planar Reconstruction with Feature Warping Guidance
https://github.com/fraunhoferivi/ssp
공식 코드https://github.com/fudan-zvg/deepinteraction
공식 코드DeepInteraction++: Multi-Modality Interaction for Autonomous Driving
https://github.com/fudan-zvg/dgmn2
공식 코드https://github.com/fudan-zvg/openocc
공식 코드OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation
https://github.com/fuenwang/LED2-Net
공식 코드LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
https://github.com/fuenwang/LayoutMP3D
공식 코드https://github.com/fyu/drn
공식 코드https://github.com/gabriellm2003/remote_sensing_missing_data
공식 코드Facing the Void: Overcoming Missing Data in Multi-View Imagery
https://github.com/gaoyuan2/apcotta
공식 코드APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
https://github.com/garrickbrazil/M3D-RPN
공식 코드M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.