Papers with Code 아카이브

Scene Parsing

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/CSAILVision/unifiedparsing

공식 코드

Unified Perceptual Parsing for Scene Understanding

https://github.com/CVLAB-Unibo/omeganet

공식 코드

Distilled Semantics for Comprehensive Scene Understanding from Videos

https://github.com/CXH-Research/DHAN-SHR

공식 코드

Dual-Hybrid Attention Network for Specular Highlight Removal

https://github.com/CYVincent/Scene-Graph-Transformer-CogTree

공식 코드

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

https://github.com/Cadene/block.bootstrap.pytorch

공식 코드

BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

https://github.com/Canjie-Luo/MORAN_v2

공식 코드

A Multi-Object Rectified Attention Network for Scene Text Recognition

https://github.com/Canjie-Luo/Scene-Text-Image-Transformer

공식 코드

Decoupled Attention Network for Text Recognition

https://github.com/Cavendish518/LE-Nav

공식 코드

Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation

https://github.com/Chat-3D/Chat-3D

공식 코드

Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes

https://github.com/Chenyang-Lu/semantic-foreground-inpainting

공식 코드

Semantic Foreground Inpainting from Weak Supervision

https://github.com/ChuanxinSong/SRRM

공식 코드

SRRM: Semantic Region Relation Model for Indoor Scene Recognition

https://github.com/CyrilSterling/LPV

공식 코드

Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition

https://github.com/DTaoo/Multimodal-Aerial-Scene-Recognition

공식 코드

Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition

https://github.com/Danial-Qashqai/CSFNet

공식 코드

CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes

https://github.com/Dayan-Guan/DA-VSN

공식 코드

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

https://github.com/DiffusionLight/DiffusionLight

공식 코드

DiffusionLight: Light Probes for Free by Painting a Chrome Ball

https://github.com/DirtyHarryLYL/HAKE-Action-Torch

공식 코드

HAKE: A Knowledge Engine Foundation for Human Activity Understanding

https://github.com/Dong-JinKim/DenseRelationalCaptioning

공식 코드

Dense Relational Image Captioning via Multi-task Triple-Stream Networks

https://github.com/DriveVLA/OpenDriveVLA

공식 코드

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

https://github.com/Earth-Intelligence-Lab/vleo-bench

공식 코드

Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data

https://github.com/EmbodiedVision/cosection

공식 코드

Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection Constraints

https://github.com/FacePerceiver/FaRL

공식 코드

General Facial Representation Learning in a Visual-Linguistic Manner

https://github.com/FangShancheng/ABINet

공식 코드

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition

https://github.com/FreeformRobotics/BORM

공식 코드

BORM: Bayesian Object Relation Model for Indoor Scene Recognition

https://github.com/FreeformRobotics/OTS

공식 코드

Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition

https://github.com/GAP-LAB-CUHK-SZ/SAMPro3D

공식 코드

SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation

https://github.com/GAP-LAB-CUHK-SZ/TO-Scene

공식 코드

TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes

https://github.com/GATECH-EIC/Omni-Recon

공식 코드

Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields

https://github.com/GOALCLEOPATRA/MLM

공식 코드

MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities

https://github.com/GatorSense/MIMRF

공식 코드

Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty

https://github.com/GeWu-Lab/MUSIC-AVQA

공식 코드

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

https://github.com/Geo-Tell/AncRec

공식 코드

Shape Anchor Guided Holistic Indoor Scene Understanding

https://github.com/GewelsJI/FSNet

공식 코드

Full-Duplex Strategy for Video Object Segmentation

https://github.com/GiuliaDAngelo/Speckegomotion

공식 코드

Wandering around: A bioinspired approach to visual attention through object motion sensitivity

https://github.com/GradientSpaces/CrossOver

공식 코드

CrossOver: 3D Scene Cross-Modal Alignment

https://github.com/GradientSpaces/LivingScenes

공식 코드

Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.