Related papers: ComplexBench-Edit: Benchmarking Complex Instructio…
Diffusion models have significantly improved the performance of image editing. Existing methods realize various approaches to achieve high-quality image editing, including but not limited to text control, dragging operation, and…
In recent years, instruction-based image editing methods have garnered significant attention in image editing. However, despite encompassing a wide range of editing priors, these methods are helpless when handling editing tasks that are…
Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the…
Instruction-based image editing has garnered significant attention due to its direct interaction with users. However, real-world user instructions are immensely diverse, and existing methods often fail to generalize effectively to…
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…
This study investigates the robustness of image classifiers to text-guided corruptions. We utilize diffusion models to edit images to different domains. Unlike other works that use synthetic or hand-picked data for benchmarking, we use…
While Instruction-based Image Editing (IIE) has achieved significant progress, existing benchmarks pursue task breadth via mixed evaluations. This paradigm obscures a critical failure mode crucial in professional applications: the…
Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…
Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and…
Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and…
Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability…
Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning,…
The evaluation of visual editing models remains fragmented across methods and modalities. Existing benchmarks are often tailored to specific paradigms, making fair cross-paradigm comparisons difficult, while video editing lacks reliable…
Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing…
In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language instructions. However, an important yet underexplored research…
Current text-to-image editing models often encounter challenges with smoothly manipulating multiple attributes using a single instruction. Taking inspiration from the Chain-of-Thought prompting technique utilized in language models, we…
Text-guided image editing, a pivotal task in modern multimedia content creation, has seen remarkable progress with training-free methods that eliminate the need for additional optimization. Despite recent progress, existing methods are…
Instruction-based multimodal image manipulation has recently made rapid progress. However, existing evaluation methods lack a systematic and human-aligned framework for assessing model performance on complex and creative editing tasks. To…
We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluation of instruction-following vision-language models for real-world use. Our starting point is curating 70 'instruction families' that we envision instruction…