Papers with Code 아카이브

Scene Understanding

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/pandapan01/evssc

공식 코드

Event-aided Semantic Scene Completion

https://github.com/pansanity666/INO_VOS

공식 코드

In-N-Out Generative Learning for Dense Unsupervised Video Segmentation

https://github.com/paulgay/VGfM

공식 코드

Visual Graphs from Motion (VGfM): Scene understanding with object geometry reasoning

https://github.com/pavliclab/aaai2022-clear2022-visual_relationship_detection-rwfn

공식 코드

Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection

https://github.com/pcasolab/vdst-net

공식 코드

Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video

https://github.com/pemami4911/segregate-relate-imagine

공식 코드

Towards Improving the Generation Quality of Autoregressive Slot VAEs

https://github.com/pengtaojiang/tsp6k

공식 코드

Traffic Scene Parsing through the TSP6K Dataset

https://github.com/phermosilla/msm

공식 코드

Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding

https://github.com/phiphiphi31/DMB

공식 코드

Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking

https://github.com/phyllish/nmp

공식 코드

Neural Message Passing for Visual Relationship Detection

https://github.com/pinxueguo/x-prompt

공식 코드

X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation

https://github.com/pipixin321/holmesvau

공식 코드

Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity

https://github.com/pjlab-adg/gpt4v-ad-exploration

공식 코드

On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

https://github.com/pkyong95/PCVOS

공식 코드

Per-Clip Video Object Segmentation

https://github.com/plusmultiply/mprm

공식 코드

Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds

https://github.com/ponimatkin/ssl-vos

공식 코드

A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation

https://github.com/pqhieu/JSIS3D

공식 코드

JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields

https://github.com/praneeth11009/LIGHTEN-Learning-Interactions-with-Graphs-and-Hierarchical-TEmporal-Networks-for-HOI

공식 코드

LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos

https://github.com/pratulsrinivasan/lighthouse

공식 코드

Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination

https://github.com/prbonn/3diss

공식 코드

Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving

https://github.com/prbonn/simp

공식 코드

Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localization

https://github.com/prgumd/0-MMS

공식 코드

0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera

https://github.com/princeton-computational-imaging/DirtyPixels

공식 코드

Dirty Pixels: Towards End-to-End Image Processing and Perception

https://github.com/prismformore/InvPT

공식 코드

InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding

https://github.com/prismformore/multi-task-transformer

공식 코드

InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding

https://github.com/probcomp/threedp3

공식 코드

3DP3: 3D Scene Perception via Probabilistic Programming

https://github.com/prs-eth/marigold

공식 코드

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

https://github.com/public-bots/gaussianpretrain

공식 코드

GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving

https://github.com/qncsn2016/TR2

공식 코드

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

https://github.com/qwtforgithub/cdsegnet

공식 코드

An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models

https://github.com/raileye3d/raileye3d_dataset

공식 코드

RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety

https://github.com/rascalgdd/vpseg

공식 코드

Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes

https://github.com/raymondwang987/nvds

공식 코드

NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

https://github.com/rbler1234/ost-bench

공식 코드

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

https://github.com/remcoroyen/vx-s3dis

공식 코드

RESSCAL3D++: Joint Acquisition and Semantic Segmentation of 3D Point Clouds

https://github.com/renezurbruegg/icg_benchmark

공식 코드

ICGNet: A Unified Approach for Instance-Centric Grasping

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