TextWand unifies scene text removal, generation and replacement via rendering/erasure decomposition, ORPE for layout fidelity, RAS for clean erasure, and the new TextWand-Bench dataset, claiming superior accuracy and quality over prior models.
Postercraft: Rethinking high-quality aesthetic poster generation in a unified framework
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 7representative citing papers
The paper presents a new automated evaluation framework for design video generation organized across layout fidelity, motion correctness, temporal quality, and content fidelity, with released code and dataset.
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
GenEvolve introduces a self-evolving agent framework for image generation using tool-orchestrated trajectories and Visual Experience Distillation to achieve claimed SOTA results on benchmarks.
SimplePoster achieves 98.7% subject preservation and improved text accuracy in product posters via full-parameter fine-tuning of an inpainting model and zero-cost character-level position encoding, outperforming complex baselines like SeedEdit 3.0.
citing papers explorer
-
TextWand: A Unified Framework for Scene Text Editing
TextWand unifies scene text removal, generation and replacement via rendering/erasure decomposition, ORPE for layout fidelity, RAS for clean erasure, and the new TextWand-Bench dataset, claiming superior accuracy and quality over prior models.
-
Evaluating Design Video Generation: Metrics for Compositional Fidelity
The paper presents a new automated evaluation framework for design video generation organized across layout fidelity, motion correctness, temporal quality, and content fidelity, with released code and dataset.
-
Advancing Aesthetic Image Generation via Composition Transfer
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
-
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
GenEvolve introduces a self-evolving agent framework for image generation using tool-orchestrated trajectories and Visual Experience Distillation to achieve claimed SOTA results on benchmarks.
-
simpleposter: a simple baseline for product poster generation
SimplePoster achieves 98.7% subject preservation and improved text accuracy in product posters via full-parameter fine-tuning of an inpainting model and zero-cost character-level position encoding, outperforming complex baselines like SeedEdit 3.0.