https://github.com/chengzhag/Implicit3DUnderstanding
공식 코드Holistic 3D Scene Understanding from a Single Image with Implicit Representation
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/chikap421/mseg_vcuq
공식 코드https://github.com/chikap421/videosam
공식 코드VideoSAM: A Large Vision Foundation Model for High-Speed Video Segmentation
https://github.com/choi58/mtcm
공식 코드Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation
https://github.com/choyingw/SCADC-DepthCompletion
공식 코드Scene Completeness-Aware Lidar Depth Completion for Driving Scenario
https://github.com/chungmin99/garfield
공식 코드https://github.com/cilinyan/VISA
공식 코드VISA: Reasoning Video Object Segmentation via Large Language Models
https://github.com/cilinyan/revos-api
공식 코드VISA: Reasoning Video Object Segmentation via Large Language Models
https://github.com/claudiacuttano/samwise
공식 코드SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
https://github.com/cmsflash/global-context-module
공식 코드Fast Video Object Segmentation using the Global Context Module
https://github.com/cognitiveaisystems/3dgraphllm
공식 코드3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
https://github.com/coldmanck/RVL-BERT
공식 코드Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
https://github.com/coldmanck/recovering-unbiased-scene-graphs
공식 코드https://github.com/colorfulfuture/awesome-trajectory-motion-prediction-papers
공식 코드https://github.com/columbia-ai-robotics/semantic-abstraction
공식 코드Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models
https://github.com/congvvc/instructseg
공식 코드InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
https://github.com/csimo005/summit
공식 코드SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
https://github.com/csiro-robotics/WildScenes
공식 코드WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments
https://github.com/cszyzhang/riconv2
공식 코드RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
https://github.com/cugbrs/MLRSNet
공식 코드https://github.com/cvg/labelmaker
공식 코드ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
https://github.com/cvlab-kaist/SOLA
공식 코드Referring Video Object Segmentation via Language-aligned Track Selection
https://github.com/cvmi-lab/pla
공식 코드https://github.com/cvmi-lab/slotmim
공식 코드A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
https://github.com/cxqnet/masseg
공식 코드https://github.com/cxx226/dpf
공식 코드https://github.com/cyuan-sjtu/vit-asym
공식 코드Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement
https://github.com/d-rothen/bmhrl
공식 코드https://github.com/daniel3303/storyreasoning
공식 코드StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
https://github.com/daniellli/lion
공식 코드https://github.com/daniellli/pad
공식 코드https://github.com/danielshkao/thinkvideo
공식 코드ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts
https://github.com/daoyuan98/sdt-hoi
공식 코드https://github.com/davidmchan/clair-a
공식 코드CLAIR-A: Leveraging Large Language Models to Judge Audio Captions
https://github.com/dawn-lx/openvoc-vidvrd
공식 코드Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
https://github.com/dawn-lx/vidvrd-tracklets
공식 코드Video Relation Detection via Tracklet based Visual Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.