SOURCE-LINKED INTELLIGENCE

MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Monocular 3D hand and body mesh recovery often suffers from severe occlusion and ambiguity. Traditional deterministic methods typically regress a single optimal solution, leading to overconfident predictions. In this paper, we introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection. Specifically, during exploration, based on our probabilistic formulation and entropy maximization, we propose a novel multi-hypothesis method referred to as MHE-Former. It is a Transformer-based multi-hypothesis framework, ensuring high training effic

Read original source ↗ Open in workspace

recordType

paper

region

Global