There are 2 repositories under motion-forecasting topic.
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
[CVPR 2023] Query-Centric Trajectory Prediction
[ICCV-2023] Official code for work "HumanMAC: Masked Motion Completion for Human Motion Prediction".
(ECCV 2020) PiP: Planning-informed Trajectory Prediction for Autonomous Driving
[ICCV21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch.
[CoRL-2022] SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving
[ICCV2023] Official PyTorch Implementation of "BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction". ICCV 2023
Code for: "Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation" Accepted @ ECCV2022
Forecasting Characteristic 3D Poses of Human Actions (CVPR'22) 🏃♂️
Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"
[CVPR22] Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
Behavior Prediction in Autonomous Driving
[IROS 2023] "Streaming Motion Forecasting for Autonomous Driving"
[ECCV 2022 Oral] Official Implementation of "Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-Agent Trajectory Prediction"
Summarized versions of certain datasets for fast iteration.
[ICCV'21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch, for Social-STGCNN on trajectory forecasting.
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"
We introduce a novel trajectory predictor that considers social interactions among agents, maintaining spatial-temporal information over an extended temporal horizon. It achieves high accuracy, generalisability, and outperforms recent SOTA algorithms on NGSIM and HIGHD Datasets
My work for the kaggle competition for CSE 151B involving motion forecasting for vehicles using the Argoverse Dataset