Related papers: SEED-Data-Edit Technical Report: A Hybrid Dataset …
We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical plausibility. Unlike existing image editing datasets that…
Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier…
We study instruction-guided editing of egocentric videos for interactive AR applications. While recent AI video editors perform well on third-person footage, egocentric views present unique challenges - including rapid egomotion and…
We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this…
Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving,…
Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation,…
We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks,…
Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which…
We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…
This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of…
Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage…
Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this…
Models for egocentric 3D and 4D reconstruction, including few-shot interpolation and extrapolation settings, can benefit from having images from exocentric viewpoints as supervision signals. No existing dataset provides the necessary…
Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor coverage of realistic editing scenarios. Meanwhile, current SED…
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operations are…
Visually-guided image editing, where edits are conditioned on both visual cues and textual prompts, has emerged as a powerful paradigm for fine-grained, controllable content generation. Although recent generative models have shown…
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…
Text-guided 3D motion editing has seen success in single-person scenarios, but its extension to multi-person settings is less explored due to limited paired data and the complexity of inter-person interactions. We introduce the task of…
The combination of language processing and image processing keeps attracting increased interest given recent impressive advances that leverage the combined strengths of both domains of research. Among these advances, the task of editing an…
We introduce mEdIT, a multi-lingual extension to CoEdIT -- the recent state-of-the-art text editing models for writing assistance. mEdIT models are trained by fine-tuning multi-lingual large, pre-trained language models (LLMs) via…