cs.CVNov 18, 2026

TRoPE: Topology-aware Relative Positional Encoding for 4D Generation

Authors: Chengzhuo Gui, Zhenglin Zhou, Fan Ma, Zongxin Yang, Yi Yang

Organizations: Zhejiang University

Abstract

Video-to-4D mesh generation has made substantial progress in recovering dynamic 3D geometry and motion from monocular videos. However, commonly used feed-forward approaches remain prone to sticking artifacts, where geodesically distant vertices move together incorrectly when they become spatially close. We attribute this failure to cross-part motion leakage: spatially nearby yet structurally distant vertices may retrieve similar motion information when motion decoding fails to distinguish spatial proximity from mesh connectivity. To address this issue, we introduce TRoPE, a topology-aware relative positional encoding that makes mesh connectivity explicit in the interaction between vertex queries and mesh-supported motion sources. TRoPE derives spectral features from the graph Laplacian and constructs pairwise topological relations from distances between multi-scale diffusion features, using these relations to modulate vertex--anchor attention through rotary phases. We further introduce a vertex-wise tail-risk objective that emphasizes persistently high-error vertices to explicitly suppress sticking artifacts. To better characterize and quantify these failures, we introduce MeshSticking-4D, a dedicated benchmark for this failure mode. Experiments on MeshSticking-4D show that TRoPE suppresses sticking artifacts while improving overall motion accuracy. Compared with the baseline, it reduces the worst-vertex error by 39.4% and lowers the separation failure rate from 49.35% to 34.90%. Additional evaluations on Motion-80 and Motion324-Subset show lower tail errors on diverse objects, while transfer to Mesh4D demonstrates applicability across backbones.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

    May 19, 2026Dvir Samuel, Yuval Atzmon, Gal Chechik +13D Mesh Generation4D Reconstruction

  2. Helix4D: Complex 4D Mesh Generation

    May 25, 2026Jiraphon Yenphraphai, Jianqi Chen, Jian Wang +63D Mesh GenerationPositional Encoding

  3. Feed-forward Motion In-betweening for Any 4D

    Jun 20, 2026Hiroki Nishizawa, Hubert P. H. Shum, Yoshihiro Fukuhara +23D Mesh Generation