相关论文: ChronoEdit: Towards Temporal Reasoning for Image E…
Video summarization aims to select keyframes that are visually diverse and can represent the whole story of a given video. Previous approaches have focused on global interlinkability between frames in a video by temporal modeling. However,…
Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…
Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing…
Recent advances in creative AI have enabled the synthesis of high-fidelity images and videos conditioned on language instructions. Building on these developments, text-to-video diffusion models have evolved into embodied world models (EWMs)…
Recent progress in large language models (LLMs) has shown that reasoning improves when intermediate thoughts are externalized into explicit workspaces, such as chain-of-thought traces or tool-augmented reasoning. Yet, visual language models…
Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous driving. However, current benchmarks fail to rigorously evaluate…
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…
We introduce \textit{Preserve Anything}, a novel method for controlled image synthesis that addresses key limitations in object preservation and semantic consistency in text-to-image (T2I) generation. Existing approaches often fail (i) to…
In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models…
Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on…
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…
Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…
Humans inhabit a physical 4D world where geometric structure and semantic content evolve over time, constituting a dynamic 4D reality (spatial with temporal dimension). While current Multimodal Large Language Models (MLLMs) excel in static…
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains…
In-context image editing aims to modify images based on a contextual sequence comprising text and previously generated images. Existing methods typically depend on task-specific pipelines and expert models (e.g., segmentation and…
Recent advancements in video generation models have significantly improved their ability to follow text prompts. However, the customization of dynamic visual effects, defined as temporally evolving and appearance-driven visual phenomena…
The recent advances in deep learning have made it possible to generate photo-realistic images by using neural networks and even to extrapolate video frames from an input video clip. In this paper, for the sake of both furthering this…
Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view…