Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
Pixel3dmm: Versatile screen-space priors for single-image 3d face reconstruction.arXiv preprint arXiv:2505.00615
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 11roles
background 1polarities
background 1representative citing papers
Introduces the ProfileSynth dataset and a profile-specific FLAME 3DMM regression baseline with visibility-aware jawline regularization for 3D reconstruction from single lateral face images.
GeoFace generates consistent multi-view face images and 3D geometry from one input via a dual-stream diffusion framework with geometry-guided attention alignment.
SHELLS uses coarse-guided layered surface sampling to achieve topologically consistent multi-view 3D head reconstruction with 88% less GPU memory, 21-29% lower registration error, and 3.5x speedup versus volumetric baselines, trained only on synthetic data.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
A transformer-based model jointly predicts depth and canonical facial coordinates to achieve unified, feed-forward 4D face reconstruction and dense tracking from image sequences.
FlexAvatar introduces bias sinks in a transformer to unify monocular and multi-view training, yielding complete 3D head avatars with strong generalization and view extrapolation from single images.
DenseMarks learns a canonical 3D embedding space for human head images by training a Vision Transformer with contrastive loss on pairwise point tracks from in-the-wild videos, plus landmark and segmentation supervision.
SuperFace refines ARKit facial expression estimation by using human preference feedback on rendered faces to optimize beyond noisy pseudo-label supervision from capture software.
citing papers explorer
-
Loki: Representation over Architecture for Diffusion-Based Portrait Animation
Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
-
Profile-Specific 3DMM Regression from a Single Lateral Face Image
Introduces the ProfileSynth dataset and a profile-specific FLAME 3DMM regression baseline with visibility-aware jawline regularization for 3D reconstruction from single lateral face images.
-
GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion
GeoFace generates consistent multi-view face images and 3D geometry from one input via a dual-stream diffusion framework with geometry-guided attention alignment.
-
Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
SHELLS uses coarse-guided layered surface sampling to achieve topologically consistent multi-view 3D head reconstruction with 88% less GPU memory, 21-29% lower registration error, and 3.5x speedup versus volumetric baselines, trained only on synthetic data.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
-
Face Anything: 4D Face Reconstruction from Any Image Sequence
A transformer-based model jointly predicts depth and canonical facial coordinates to achieve unified, feed-forward 4D face reconstruction and dense tracking from image sequences.
-
FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision
FlexAvatar introduces bias sinks in a transformer to unify monocular and multi-view training, yielding complete 3D head avatars with strong generalization and view extrapolation from single images.
-
Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
DenseMarks learns a canonical 3D embedding space for human head images by training a Vision Transformer with contrastive loss on pairwise point tracks from in-the-wild videos, plus landmark and segmentation supervision.
-
SuperFace: Preference-Aligned Facial Expression Estimation Beyond Pseudo Supervision
SuperFace refines ARKit facial expression estimation by using human preference feedback on rendered faces to optimize beyond noisy pseudo-label supervision from capture software.
- Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image