← Search

Yongchuan Tang

2 accepted papers

2025

PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs

ICCV 2025poster

Panoramic Image Generation (PIG) aims to create coherent images of arbitrary lengths. Most existing methods fall in the joint diffusion paradigm, but their complex and heuristic crop connection designs often limit their ability to achieve multilevel coherence. By deconstructing this challenge into i…

2021

Image Synthesis From Layout With Locality-Aware Mask Adaption

ICCV 2021poster

This paper is concerned with synthesizing images conditioned on a layout (a set of bounding boxes with object categories). Existing works construct a layout-mask-image pipeline. Object masks are generated separately and mapped to bounding boxes to form a whole semantic segmentation mask (layout-to-m…

Cited by 80PDFcodeScholar