Personalizing text-to-image models to generate images of specific subjects across diverse scenes and styles is a rapidly advancing field. Current approaches often face challenges in maintaining a balance between identity preservation and alignment with the input text prompt. Some methods rely on a single textual token to represent a subject, which limits expressiveness, while others employ richer representations but disrupt the model’s prior, diminishing prompt alignment. In this work, we introduce Nested Attention, a novel mechanism that injects a rich and expressive image representation into the model’s existing cross-attention layers. Our key idea is to generate query-dependent subject values, derived from nested attention layers that learn to select relevant subject features for each region in the generated image. We integrate these nested layers into an encoder-based personalization method, and show that they enable high identity preservation while adhering to input text prompts. Our approach is general and can be trained on various domains. Additionally, its prior preservation allows us to combine multiple personalized subjects from different domains in a single image.
论文检索
输入标题、作者或关键词，从 306 篇学术成果中精准定位
GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
PDF ↗Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric distortions, excessive cropping, poor generalization) that degrade the user experience. To address these issues, we introduce GaVS, a novel 3D-grounded approach that reformulates video stabilization as a temporally-consistent ‘local reconstruction and rendering’ paradigm. Given 3D camera poses, we augment a reconstruction model to predict Gaussian Splatting primitives, and finetune it at test-time, with multi-view dynamics-aware photometric supervision and cross-frame regularization, to produce temporally-consistent local reconstructions. The model are then used to render each stabilized frame. We utilize a scene extrapolation module to avoid frame cropping. Our method is evaluated on a repurposed dataset, instilled with 3D-grounded information, covering samples with diverse camera motions and scene dynamics. Quantitatively, our method is competitive with or superior to state-of-the-art 2D and 2.5D approaches in terms of conventional task metrics and new geometry consistency. Qualitatively, our method produces noticeably better results compared to alternatives, validated by the user study. Project Page: sinoyou.github.io/gavs.
In this work, we present a novel approach for motion customization in video generation, addressing the widespread gap in the exploration of motion representation within video generative models. Recognizing the unique challenges posed by the spatiotemporal nature of video, our method introduces Motion Embeddings, a set of explicit, temporally coherent embeddings derived from a given video. These embeddings are designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity. Our approach provides a compact and efficient solution to motion representation, utilizing two types of embeddings: a Motion Query-Key Embedding to modulate the temporal attention map and a Motion Value Embedding to modulate the attention values. Additionally, we introduce an inference strategy that excludes spatial dimensions from the Motion Query-Key Embedding and applies a debias operation to the Motion Value Embedding, both designed to debias appearance and ensure the embeddings focus solely on motion. Our contributions include the introduction of a tailored motion embedding for customization tasks and a demonstration of the practical advantages and effectiveness of our method through extensive experiments. Project page: https://wileewang.github.io/MotionInversion/
Walk on stars (WoSt) has shown its power in being applied to Monte Carlo methods for solving partial differential equations, but the sampling techniques in WoSt are not satisfactory, leading to high variance. We propose a guiding-based importance sampling method to reduce the variance of WoSt. Drawing inspiration from path guiding in rendering, we approximate the directional distribution of the recursive term of WoSt using online-learned parametric mixture distributions, decoded by a lightweight neural field. This adaptive approach enables importance sampling the recursive term, which lacks shape information before computation. We introduce a reflection technique to represent guiding distributions at Neumann boundaries and incorporate multiple importance sampling with learnable selection probabilities to further reduce variance. We also present a practical GPU implementation of our method. Experiments show that our method effectively reduces variance compared to the original WoSt, given the same time or the same sample budget. Code and data for this paper are at https://github.com/tyanyuy3125/elaina.
Automated tools for video editing and assembly have applications ranging from filmmaking and advertisement to content creation for social media. Previous video editing work has mainly focused on either retrieval or user interfaces, leaving actual editing to the user. In contrast, we propose to automate the core task of video editing, formulating it as sequential decision making process. Ours is a multi-agent approach. We design an Editor agent and a Critic agent. The Editor takes as input a collection of video clips together with natural language instructions and uses tools commonly found in video editing software to produce an edited sequence. On the other hand, the Critic gives natural language feedback to the editor based on the produced sequence or renders it if it is satisfactory. We introduce a learning-based approach for enabling effective communication across specialized agents to address the language-driven video editing task. Finally, we explore an LLM-as-a-judge metric for evaluating the quality of video editing system and compare it with general human preference. We evaluate our system’s output video sequences qualitatively and quantitatively through a user study and find that our system vastly outperforms existing approaches in terms of coverage, time constraint satisfaction, and human preference. Please see our companion supplemental video for qualitative results.
Recent research on generative models has primarily focused on creating product-ready visual outputs; however, designers often favor access to standardized asset libraries, a domain that has yet to be significantly enhanced by generative capabilities. Although open-world scenes provide ample raw materials for designers, efficiently extracting high-quality, standardized assets remains a challenge. To address this, we introduce AssetDropper, the first generative framework designed to extract any asset from reference images, providing artists with an open-world asset palette. Our model adeptly extracts a front view of selected subjects from input images, effectively handling complex scenarios such as perspective distortion and subject occlusion. We establish a synthetic dataset of more than 200,000 image-subject pairs and a real-world benchmark with thousands more for evaluation, facilitating the exploration of future research in downstream tasks. Furthermore, to ensure precise asset extraction that aligns well with the image prompts, we employ a pre-trained reward model to achieve a closed loop with feedback. We design the reward model to perform an inverse task that pastes the extracted assets back into the reference sources, which assists training with additional consistency and mitigates hallucination. Extensive experiments show that, with the aid of reward-driven optimization, AssetDropper achieves the state-of-the-art results in asset extraction. Our code and dataset are available at https://github.com/Lanjiong-Li/AssetDropper.