visual priors

4 papers

• Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
• Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation
• SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
• Video Perception Models for 3D Scene Synthesis