3d gaussian representation 1facial motion refinement 1head avatar reconstruction 1incremental reconstruction 1sparse-to-dense learning 1transformer architecture 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
Jianjiang Yao, Ke Xian, Renxiang Dai +1
The paper introduces FFAvatar, a transformer-based 3D Gaussian framework that can quickly build high‑quality, animatable 4D head avatars from one or more portrait images, supportin…
cs.AI2026
Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning
Peng, Lee, Yin Zhang +9
Reinforcement Learning (RL) is an important paradigm for improving the reasoning capabilities of Vision-Language Models (VLMs). However, directly applying RL to rollout multimodal…