realistic traffic agent modeling
1.Optimizing diffusion models for joint trajectory prediction and controllable generation
https://arxiv.org/pdf/2408.00766 2024, 7 1회 인용 ECCV 2024 https://github.com/YixiaoWang7/OptTrajDiff 31 stars 논문 이해도 현황: 하 지속적 업데이트 예정입니다. 바쁘신 분들을 위한 3줄 요약 Controllable multi-agent Traffic g...
2.[generation][22, 3][203] Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
https://openaccess.thecvf.com/content/CVPR2022/papers/Gu_Stochastic_Trajectory_Prediction_via_Motion_Indeterminacy_Diffusion_CVPR_2022_paper.pdf2
3.[generation][22, 10][129]Guided Conditional Diffusion for Controllable Traffic Simulation
데모: https://aiasd.github.io/ctg.github.io 논문: https://arxiv.org/pdf/2210.17366 코드: https://github.com/NVlabs/CTG -1. 세줄 요약 signal temporal logic (STL
4.[generation][23, 6][86] MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion
https://openaccess.thecvf.com/content/CVPR2023/papers/JiangMotionDiffuserControllableMulti-AgentMotionPredictionUsingDiffusionCVPR2023paper.pdf 0. 핵심
5.[generation][23.4][85] Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
작성중
6.Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
scene initialization자율주행 시뮬레이션을 돌릴 때, 제일 처음 시작하는 환경 구성도로: 도로 차선 갯수, 모양, 차선 간 연결 관계 등agent차량/사람/자전거/정적 장애물 등의 초기 상태여기서 초기상태는, 위치/속도/방향/차 크기/종류 를 의미기존 시