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/genintel/datasetnerf
공식 코드DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
https://github.com/gewu-lab/crab
공식 코드Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
https://github.com/gewu-lab/mwafm
공식 코드https://github.com/gkw0010/endochat
공식 코드EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery
https://github.com/google-research-datasets/2.5vrd
공식 코드https://github.com/google-research/cad-estate
공식 코드https://github.com/google-research/scenic
공식 코드Unified Visual Relationship Detection with Vision and Language Models
https://github.com/google-research/snap
공식 코드SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding
https://github.com/gorilla-lab-scut/sstnet
공식 코드Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
https://github.com/griffbr/BubbleNets
공식 코드https://github.com/griffbr/ODMS
공식 코드Learning Object Depth from Camera Motion and Video Object Segmentation
https://github.com/griffbr/TIS
공식 코드https://github.com/griffbr/supervoxel-gerrymandering
공식 코드Video Object Segmentation using Supervoxel-Based Gerrymandering
https://github.com/gruberto/Gated2Depth
공식 코드https://github.com/guoleisun/indiscernible-object-counting
공식 코드https://github.com/guoleisun/vss-cffm
공식 코드Learning Local and Global Temporal Contexts for Video Semantic Segmentation
https://github.com/guoleisun/vss-mrcfa
공식 코드Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation
https://github.com/guoyongcs/AEGAN
공식 코드Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
https://github.com/gwenzhang/GGA
공식 코드General Geometry-aware Weakly Supervised 3D Object Detection
https://github.com/hailieqh/3d-object-primitive-graph
공식 코드Single Image 3D Object Estimation with Primitive Graph Networks
https://github.com/hanxunyu/inst3d-lmm
공식 코드Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
https://github.com/haochenheheda/SwiftNet
공식 코드https://github.com/haochenz11/iref-vla
공식 코드IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes
https://github.com/happy-hsy/motionmae
공식 코드Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders
https://github.com/harboryuan/polyphonicformer
공식 코드PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
https://github.com/harkiratbehl/MetaVOS
공식 코드Meta Learning Deep Visual Words for Fast Video Object Segmentation
https://github.com/harrytea/adaptvision
공식 코드AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
https://github.com/harrytea/root
공식 코드ROOT: VLM based System for Indoor Scene Understanding and Beyond
https://github.com/hashmatshadab/apr
공식 코드Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
https://github.com/hasibzunair/rsud20k
공식 코드RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving
https://github.com/havrylovv/isegprobe
공식 코드Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation
https://github.com/hebeifast/eventlowlightvos
공식 코드https://github.com/helen1c/mc-panda
공식 코드https://github.com/heng-hw/spacap3d
공식 코드Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds
https://github.com/henghuiding/MOSE-api
공식 코드MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.