AI Paper Atlas

Research map / 3D vision / 3D generation

DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video

Hao Wen, Hongbo Kang, Jian Ma, Jing Huang, Yuanwang Yang, Haozhe Lin, Yu‐Kun Lai, Kun Li

TPAMI 2025 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add coarse-to-fine group-guided motion optimization (ablation)DyCrowd · VirtualCrowdMPJPE: 86.87 -> 69.74Improved
add coarse-to-fine group-guided motion optimization (ablation)DyCrowd · VirtualCrowdACCEL: 73.33 -> 15.72Improved
add coarse-to-fine group-guided motion optimization (ablation)DyCrowd · VirtualCrowd (occluded instances)MPJPE: 73.01 -> 66.09Improved
add asynchronous motion consistency loss (ablation)DyCrowd · VirtualCrowdMPJPE: 70.22 -> 69.74Improved
add asynchronous motion consistency loss (ablation)DyCrowd · VirtualCrowdACCEL: 15.08 -> 15.72Hurt
add asynchronous motion consistency loss (ablation)DyCrowd · VirtualCrowd (occluded instances)MPJPE: 67.17 -> 66.09Improved
add asynchronous motion consistency loss (ablation)DyCrowd · VirtualCrowdW-MPJPE: 83.35 -> 83.39Hurt
use proposed VAE prior instead of NeMF (ablation)DyCrowd · VirtualCrowdMPJPE: 84.63 -> 70.22Improved
use proposed VAE prior instead of DMMR-VAE (ablation)DyCrowd · VirtualCrowdMPJPE: 84.13 -> 70.22Improved
use proposed VAE prior instead of NeMF (ablation)DyCrowd · VirtualCrowdACCEL: 13.87 -> 15.08Hurt
DyCrowd vs SLAHMR-Large under ground-truth trackingDyCrowd · VirtualCrowd (GT tracking)MPJPE: 106.35 -> 68.81Improved
DyCrowd vs SLAHMR-Large under ground-truth trackingDyCrowd · VirtualCrowd (GT tracking)ACCEL: 12.25 -> 15.53Hurt

Later papers that compared with this method

1 later accepted paper reports DyCrowd as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy