4 papers
Latent Dynamics for Full Body Avatar Animation
Shichong Peng, Chengxiang Yin, Fei Jiang +7
Pose-driven full-body avatars built on neural rendering produce high-quality novel views of a captured subject. Yet loose clothing and other dynamic elements deform in ways pose al…
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Junxuan Li, Rawal Khirodkar, Chengan He +37
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans wit…
CHOSEN: Contrastive Hypothesis Selection for Multi-View Depth Refinement
Di Qiu, Yinda Zhang, Thabo Beeler +5
We propose CHOSEN, a simple yet flexible, robust and effective multi-view depth refinement framework. It can be employed in any existing multi-view stereo pipeline, with straightfo…
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
Wufei Ma, Kai Li, Zhongshi Jiang +5
Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand…