works on
benchmark 1evaluation 1evaluation benchmark 1image editing 1large language models 1mesh reconstruction 1multi-person interaction 1multi-turn dialogue 1role-playing agents 1user simulation 1

From the 2 of 10 linked papers with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

Jiajia Lin, Mingxuan Du, Tuowen Zhou +2

The paper presents MPIE-Bench, a benchmark of 2,500 multi-person interaction editing examples, and MPIE-Eval, an evaluation method that uses mesh reconstruction to assess anatomica…