diffusion models 1implicit geometry 1metric scale 1monocular depth estimation 1novel view synthesis 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
Yufei Cai, Xuesong Niu, Hao Lu +3
MetaView is a diffusion-based framework that generates novel views from a single image by combining implicit geometry priors with metric depth cues, enabling large viewpoint change…
cs.CV2025
EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
Yufei Cai, Hu Han, Yuxiang Wei +2
The progress on generative models has led to significant advances on text-to-video (T2V) generation, yet the motion controllability of generated videos remains limited. Existing mo…