https://github.com/zhaoyucs/vsd
공식 코드Generating Visual Spatial Description via Holistic 3D Scene Understanding
Papers with Code 아카이브
Scene Parsing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 9
- 평가표
- 2
- 보존된 평가 기록
- 3
Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. MIT Description
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhe-sapi/udass
공식 코드https://github.com/zhen6618/eprecon
공식 코드EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video
https://github.com/zhenzhenxiang/SemanticsSharing
공식 코드Boosting Real-Time Driving Scene Parsing with Shared Semantics
https://github.com/zhihou7/HOI-CL
공식 코드Detecting Human-Object Interaction via Fabricated Compositional Learning
https://github.com/zhihou7/HOI-CL-OneStage
공식 코드Affordance Transfer Learning for Human-Object Interaction Detection
https://github.com/zhimin-c/bridge3d
공식 코드Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
https://github.com/zhiweihhh/cvpr2022-rvos-challenge
공식 코드1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation
https://github.com/zhonghuayi/focusflow_official
공식 코드FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving
https://github.com/zhouhaocv/RLM-Net
공식 코드https://github.com/zhousheng97/vitxt-gqa
공식 코드Scene-Text Grounding for Text-Based Video Question Answering
https://github.com/zhoustan/camsam2
공식 코드https://github.com/zht8506/qmvos
공식 코드https://github.com/zhugekongkong/sgg-g2s
공식 코드From General to Specific: Informative Scene Graph Generation via Balance Adjustment
https://github.com/zhuzi24/sgg-toolkit
공식 코드https://github.com/zhyever/monocular-depth-estimation-toolbox
공식 코드BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation
https://github.com/zifuwan/sigma
공식 코드Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
https://github.com/zihangm/Differentiable-LP-Layer
공식 코드Physarum Powered Differentiable Linear Programming Layers and Applications
https://github.com/zihangm/Physarum-Differentiable-LP-Layer
공식 코드Physarum Powered Differentiable Linear Programming Layers and Applications
https://github.com/zikai1/oareg
공식 코드Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
https://github.com/ziplab/mpvss
공식 코드https://github.com/zitongzhan/mmtracking/tree/zitongzhan/rovis/configs/vis/rovis
공식 코드Robust Online Video Instance Segmentation with Track Queries
https://github.com/zixiliang/s-inf
공식 코드S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field
https://github.com/zju-jiangqi/ciada
공식 코드Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations
https://github.com/zlai0/CorrFlow
공식 코드https://github.com/zlai0/MAST
공식 코드https://github.com/zn-qiao/deep-narrow-network
공식 코드https://github.com/zonmgin-zhang/asi-seg
공식 코드ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding
https://github.com/zouchuhang/LayoutNetv2
공식 코드LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
https://github.com/zrrskywalker/personalize-sam
공식 코드https://github.com/zty0304/sgdraw
공식 코드SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation
https://github.com/zubair-irshad/NeRF-MAE
공식 코드https://github.com/zyp123494/dynavol
공식 코드Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering
https://github.com/zzhhfut/ccnet-aaai2025
공식 코드https://github.com/zzy-zhou/dsec-mos
공식 코드Event-Free Moving Object Segmentation from Moving Ego Vehicle
https://github.com/zzzkkkyyy/padenet
공식 코드Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.