SplatShot is a training-free method that inserts per-step 3DGS refitting and photometric feedback into diffusion denoising to enforce multi-view consistency for single-photo 3D face avatars.
Real3d-portrait: One- shot realistic 3d talking portrait synthesis
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 10roles
baseline 1polarities
baseline 1representative citing papers
AvatarPointillist autoregressively generates adaptive 3D point clouds via Transformer for photorealistic 4D Gaussian avatars from one image, jointly predicting animation bindings and using a conditioned Gaussian decoder.
UIKA is a feed-forward animatable Gaussian head model using UV-guided correspondence estimation and learnable UV tokens with dual-level attention, trained on large-scale synthetic data to handle pose-free inputs.
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.
A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.
SplitAvatar applies an autoregressive graph splitting network with mesh topology extension and gated density control to generate detailed one-shot head avatars via 3D Gaussian Splatting.
SDTalk proposes a generalizable one-shot 3DGS talking head method that uses structured facial priors for complete reconstruction and dual-branch motion fields for dynamics, outperforming prior identity-specific approaches.
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.
THEval proposes eight metrics for evaluating talking head videos on quality, naturalness, and synchronization, tested on 85,000 videos from 17 models with a new curated dataset.
citing papers explorer
-
Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo
SplatShot is a training-free method that inserts per-step 3DGS refitting and photometric feedback into diffusion denoising to enforce multi-view consistency for single-photo 3D face avatars.
-
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
AvatarPointillist autoregressively generates adaptive 3D point clouds via Transformer for photorealistic 4D Gaussian avatars from one image, jointly predicting animation bindings and using a conditioned Gaussian decoder.
-
UIKA: Fast Universal Head Avatar from Pose-Free Images
UIKA is a feed-forward animatable Gaussian head model using UV-guided correspondence estimation and learnable UV tokens with dual-level attention, trained on large-scale synthetic data to handle pose-free inputs.
-
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.
-
Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs
A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.
-
SplitAvatar: One-shot Head Avatar with Autoregressive Gaussian Splitting
SplitAvatar applies an autoregressive graph splitting network with mesh topology extension and gated density control to generate detailed one-shot head avatars via 3D Gaussian Splatting.
-
SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis
SDTalk proposes a generalizable one-shot 3DGS talking head method that uses structured facial priors for complete reconstruction and dual-branch motion fields for dynamics, outperforming prior identity-specific approaches.
-
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.
-
THEval. Evaluation Framework for Talking Head Video Generation
THEval proposes eight metrics for evaluating talking head videos on quality, naturalness, and synchronization, tested on 85,000 videos from 17 models with a new curated dataset.
- Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling