5 papers
Learning Field Reconstruction from Incomplete Data by Globally Correcting Local Estimates
Renhao Zhong, Zihan Zhou, Chiyuan Ma +1
Reconstructing physical fields from training samples that are always incomplete requires learning spatial structure from fragmented observations. Existing context--query work estab…
Observation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions
Chiyuan Ma, Zihan Zhou, Tianshu Yu
Learning physical fields directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and often missing not at random, wherea…
DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
Zihan Zhou, Shilin Lu, Shuli Leng +4
Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project o…
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Shilin Lu, Zhuming Lian, Zihan Zhou +3
Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections)…
Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
Shilin Lu, Zihan Zhou, Jiayou Lu +2
Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks dur…