3 papers
cs.CV2026
TextMesh4D: Zero-shot Text-to-4D Mesh Generation
Sisi Dai, Xinxin Su, Kai Xu
Large-scale, high-quality dynamic 3D (4D) assets are essential for learning physically grounded representations, but remain costly to capture and annotate at scale. This limits the…
cs.CV2025
AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation
Sisi Dai, Kai Xu
Despite significant progress in text-driven 4D human-object interaction (HOI) generation with supervised methods, the scalability remains limited by the scarcity of large-scale 4D…
cs.CV2024
InterFusion: Text-Driven Generation of 3D Human-Object Interaction
Sisi Dai, Wenhao Li, Haowen Sun +5
In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We identify and address two k…