← Back to all news
arXiv Computer Vision By Markus Pobitzer, Chang Liu, Chenyi Zhuang, Teng Long, Bin Ren, Nicu Sebe

Loomis Painter: Learning Painting Processes by Reversing Image-to-Video Generation

Read the original on arXiv Computer Vision →

Loomis Painter is a framework that learns painting processes by training on reversed image‑to‑video sequences, preserving reference‑attention behavior and avoiding long‑range dependencies that disrupt pretrained models. It introduces a media‑transfer strategy to decouple input appearance from the target process, enabling generation across different artistic media. Evaluated on a curated dataset of real‑world painting processes, the method outperforms baselines on LPIPS, DINO, and CLIP metrics and receives consistent preference in expert and non‑expert user studies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 22

Painting Change Map as guidance for generating painting processes

The paper introduces the Painting Change Map, a spatio‑temporal control mechanism that tracks normalized structural changes across a 1,000‑timestep continuum for dynamic video generation of paintings. By encoding localized visual differences into an RGB space, it provides fine‑grained guidance for both forward painting and reverse unpainting processes. Experiments show that this approach outperforms existing control baselines and matches or exceeds state‑of‑the‑art painting methods, especially under oracle conditions.

By Markus Pobitzer, Chang Liu, Niccol\`o Biondi, Nicu Sebe
diffusionbenchmarks
More like this →
arXiv AI
2d ago

SemantiScene-Edit: Expert-Synthesized Supervision and Dual-Path Source Conditioning for Instruction-Based Video Editing

SemantiScene-Edit is a video editing system that uses a multimodal encoder and a pretrained video diffusion transformer to follow natural‑language instructions while preserving the source video’s appearance and temporal structure. The encoder processes source frames and the instruction together, sending semantic queries to the generator via a trainable connector and cross‑attention. A dual‑path visual route concatenates source‑video latents with noisy target latents to provide dense spatial and temporal information, and the model is trained with flow matching and a three‑stage curriculum on over 1.2 million instruction‑conditioned records, with a 100‑case benchmark for evaluation.

By Xinyu Chen, Song Wu, Dingbao Shao, Jiahang Li, Jiang Lin, Yuhang Liu, Duo Li, Jiaxin Hu, Shengrong Gu, Liang Li, Qian Wang, Junlan Feng, Ying Tai, Jian Yang, Zili Yi
llmsragdiffusionmultimodalbenchmarkssafety
More like this →