MOCHI enables registration-free training of multi-view 3D face reconstruction by enforcing topological consistency via a pseudo-linear inverse kinematic solver, using synthetic-data-trained 2D landmarks for alignment, and new pointmap/normal losses plus test-time optimization to outperform prior art
arXiv:2207.11094 (2022)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
A Transformer 3D-Gaussian model reconstructs incremental, animatable 4D head avatars from sparse portraits via alternating attention, sparse-to-dense UV densification, and residual motion refinement.
DyaPlex introduces a dual-tower Transformer that adds a streaming motion pathway to a frozen full-duplex speech model using dyadic token interleaving and time-aligned RoPE for synchronized multimodal dyadic interaction.
Fusing 3D facial motion descriptors with physiological signals via cross-modal attention improves stress detection AUROC from 52.7% to 92.0% on driving data.
citing papers explorer
-
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
MOCHI enables registration-free training of multi-view 3D face reconstruction by enforcing topological consistency via a pseudo-linear inverse kinematic solver, using synthetic-data-trained 2D landmarks for alignment, and new pointmap/normal losses plus test-time optimization to outperform prior art
-
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
A Transformer 3D-Gaussian model reconstructs incremental, animatable 4D head avatars from sparse portraits via alternating attention, sparse-to-dense UV densification, and residual motion refinement.
-
DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction
DyaPlex introduces a dual-tower Transformer that adds a streaming motion pathway to a frozen full-duplex speech model using dyadic token interleaving and time-aligned RoPE for synchronized multimodal dyadic interaction.
-
Combining Facial Videos and Biosignals for Stress Estimation During Driving
Fusing 3D facial motion descriptors with physiological signals via cross-modal attention improves stress detection AUROC from 52.7% to 92.0% on driving data.