https://github.com/GATECH-EIC/Omni-Recon
공식 코드Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
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/GOALCLEOPATRA/MLM
공식 코드MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities
https://github.com/GatorSense/MIMRF
공식 코드Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty
https://github.com/GeWu-Lab/MUSIC-AVQA
공식 코드Learning to Answer Questions in Dynamic Audio-Visual Scenarios
https://github.com/Geo-Tell/AncRec
공식 코드https://github.com/GewelsJI/FSNet
공식 코드https://github.com/GiuliaDAngelo/Speckegomotion
공식 코드Wandering around: A bioinspired approach to visual attention through object motion sensitivity
https://github.com/GradientSpaces/CrossOver
공식 코드https://github.com/GradientSpaces/LivingScenes
공식 코드Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
https://github.com/HCPLab-SYSU/ATEN
공식 코드Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
https://github.com/HKBU-HPML/IRS
공식 코드https://github.com/HSE-asavchenko/mobile-visual-preferences
공식 코드https://github.com/HYOJINPARK/Reuse_VOS
공식 코드Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
https://github.com/HYOJINPARK/TTVOS
공식 코드https://github.com/HeatherJiaZG/SuperGlue-pytorch
공식 코드Physarum Powered Differentiable Linear Programming Layers and Applications
https://github.com/HengyiWang/SIRNet
공식 코드Boosting Video Object Segmentation based on Scale Inconsistency
https://github.com/HenryJunW/TAG
공식 코드TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
https://github.com/Holmes-Alan/FunnyNet-W
공식 코드FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild
https://github.com/Hoyyyaard/LSceneLLM
공식 코드LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences
https://github.com/Hua-YS/Prototype-based-Memory-Network
공식 코드Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks
https://github.com/Hydragon516/PMN
공식 코드Unsupervised Video Object Segmentation via Prototype Memory Network
https://github.com/ICEORY/PMF
공식 코드EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation
https://github.com/IMSY-DKFZ/self-distilled-swin
공식 코드https://github.com/IntelVCL/MultiObjectiveOptimization
공식 코드https://github.com/JWFangit/LOTVS-DADA
공식 코드DADA: Driver Attention Prediction in Driving Accident Scenarios
https://github.com/Jacobew/AutoPanoptic
공식 코드Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
https://github.com/JingchunCheng/FAVOS
공식 코드Fast and Accurate Online Video Object Segmentation via Tracking Parts
https://github.com/JingchunCheng/SegFlow
공식 코드SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
https://github.com/Jingkang50/OpenPSG
공식 코드https://github.com/JustineGiroux/Lightsome
공식 코드Towards a Perceptual Evaluation Framework for Lighting Estimation
https://github.com/Jyxarthur/flowsam
공식 코드https://github.com/KangchengLiu/FAC_Foreground_Aware_Contrast
공식 코드Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast
https://github.com/KevinDuarte/CapsuleVOS
공식 코드CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing
https://github.com/KyanChen/OvarNet
공식 코드OvarNet: Towards Open-vocabulary Object Attribute Recognition
https://github.com/LaVi-Lab/Video-3D-LLM
공식 코드Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
https://github.com/Lavreniuk/SPIdepth
공식 코드SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.