https://github.com/willemeng/VLScene
공식 코드VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion
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/wjf5203/vnext
공식 코드https://github.com/wjn922/referformer
공식 코드https://github.com/wkentaro/reorientbot
공식 코드ReorientBot: Learning Object Reorientation for Specific-Posed Placement
https://github.com/wkentaro/safepicking
공식 코드SafePicking: Learning Safe Object Extraction via Object-Level Mapping
https://github.com/workforai/gsfm
공식 코드Global Spectral Filter Memory Network for Video Object Segmentation
https://github.com/workforai/qdmn
공식 코드Learning Quality-aware Dynamic Memory for Video Object Segmentation
https://github.com/wudongming97/onlinerefer
공식 코드OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
https://github.com/wujinhuan/3d-human-pose
공식 코드https://github.com/wuzijian1997/sis-pt-sam
공식 코드https://github.com/wyddmw/WiseAD
공식 코드WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model
https://github.com/wzzheng/stag
공식 코드Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
https://github.com/xahidbuffon/srdrm
공식 코드Underwater Image Super-Resolution using Deep Residual Multipliers
https://github.com/xavijuanola/vssl_eval
공식 코드A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio
https://github.com/xharlie/btcdet
공식 코드Behind the Curtain: Learning Occluded Shapes for 3D Object Detection
https://github.com/xheon/panoptic-reconstruction
공식 코드https://github.com/xiangxu-0103/superflow
공식 코드SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining
https://github.com/xiaoaoran/FPS-Net
공식 코드FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
https://github.com/xiaohao-xu/ambiguity-in-space
공식 코드Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
https://github.com/xiaoqi-zhao-dlut/multi-source-aps-zvos
공식 코드Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
https://github.com/xiaoqinzhe/vrdetection
공식 코드https://github.com/xilin1991/CluterNet
공식 코드Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
https://github.com/xilin1991/IMCNet
공식 코드Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
https://github.com/xing0047/tps
공식 코드Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
https://github.com/xinshuoweng/mono3D_PLiDAR
공식 코드https://github.com/xiweix/reme
공식 코드ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
https://github.com/xmed-lab/GL-Fusion
공식 코드GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation
https://github.com/xmed-lab/GraphEcho
공식 코드GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation
https://github.com/xmlyqing00/AFB-URR
공식 코드Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
https://github.com/xr-lee/neural-symbolic
공식 코드Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction
https://github.com/xujian000/daf-net
공식 코드https://github.com/xumengyaamy/p-cbls
공식 코드Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
https://github.com/xushilin1/rap-sam
공식 코드https://github.com/xvjiarui/VFS
공식 코드Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective
https://github.com/xw-hu/unveiling-deep-shadows
공식 코드https://github.com/xxlong0/CNMNet
공식 코드Occlusion-Aware Depth Estimation with Adaptive Normal Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.