5 papers
OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots
Mazhar Iqbal, Naoya Chiba, Xuanmeng Sha +2
Generating compact and geometrically faithful 3D meshes directly from point clouds remains a fundamental challenge. Point clouds are unordered and sparse, whereas meshes exhibit ir…
AcoustEmo: Open-Vocabulary Emotion Reasoning via Utterance-Aware Acoustic Q-Former
Liyun Zhang, Xuanmeng Sha, Shuqiong Wu +1
Multimodal Large Language Models (MLLMs) excel in Open-Vocabulary (OV) emotion recognition but often neglect fine-grained acoustic modeling. Existing methods typically use global a…
3DGesPolicy: Phoneme-Aware Holistic Co-Speech Gesture Generation Based on Action Control
Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita +2
Generating holistic co-speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstab…
A Unified Evaluation Framework for Multi-Annotator Tendency Learning
Liyun Zhang, Fengkai Liu, Xuanmeng Sha +3
Recent works have emerged in multi-annotator learning that shift focus from Consensus-oriented Learning (CoL), which aggregates multiple annotations into a single ground-truth pred…
3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control
Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita +2
Audio-driven 3D facial animation has achieved significant progress in both research and applications. While recent baselines struggle to generate natural and continuous facial move…