SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09640 · ICCV · 2021

DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets

Hang Zhao, Chen Sun, Junru Gu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Tsinghua-MARS-Lab/DenseTNT pwc_unofficial 2 of 4
FunctionStatusWhere it lives
batch_list_to_batch_tensors Ran Tsinghua-MARS-Lab/DenseTNT/src/utils.py
code served (permissive licence) · get_code("3581e32e0e7889a2")
load Ran Tsinghua-MARS-Lab/DenseTNT/src/structs.py
code served (permissive licence) · get_code("8a6901e812426548")
get_name Not yet run Tsinghua-MARS-Lab/DenseTNT/src/utils.py
code served (permissive licence) · get_code("cb738ca038a25cf6")
get_pad_vector Not yet run Tsinghua-MARS-Lab/DenseTNT/src/utils.py
code served (permissive licence) · get_code("19035027777a6c24")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Due to the stochasticity of human behaviors, predicting the future trajectories of road agents is challenging for autonomous driving. Recently, goal-based multi-trajectory prediction methods are proved to be effective, where they first score over-sampled goal candidates and then select a final set from them. However, these methods usually involve goal predictions based on sparse pre-defined anchors and heuristic goal selection algorithms. In this work, we propose an anchor-free and end-to-end trajectory prediction model, named DenseTNT, that directly outputs a set of trajectories from dense goal candidates. In addition, we introduce an offline optimization-based technique to provide multi-future pseudo-labels for our final online model. Experiments show that DenseTNT achieves state-of-the-art performance, ranking 1 st on the Argoverse motion forecasting benchmark and being the 1 st place winner of the 2021 Waymo Open Dataset Motion Prediction Challenge.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.09640")
get_code_for_paper("2108.09640")
have("2108.09640")

Connect an agent — have() is free.