Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning

• URL: http://arxiv.org/abs/2412.02114v2
• Date: Tue, 18 Mar 2025 10:51:59 GMT
• Title: Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
• Authors: Harold Haodong Chen, Harry Yang, Ser-Nam Lim,
• Abstract summary: UES (Unlocking Universal Editing via Self-Supervision) is a lightweight self-supervised fine-tuning strategy that transforms generation models into unified generation-editing systems.<n>Our approach establishes a dual-conditioning mechanism where original video-text pairs jointly provide visual and textual semantics.<n>To enable systematic evaluation, we introduce OmniBench-99, a comprehensive benchmark spanning 99 videos across humans/animals, environments, and objects.
• Score: 45.64777118760738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in video generation have outpaced progress in video editing, which remains constrained by several limiting factors, namely: (a) the task's dependency on supervision severely limits generality, (b) an unnecessary artificial separation between the generation and editing task, and (c) the high computational costs of training a video model. In this work, we propose UES (Unlocking Universal Editing via Self-Supervision), a lightweight self-supervised fine-tuning strategy that transforms generation models into unified generation-editing systems through self-supervised semantic alignment. Our approach establishes a dual-conditioning mechanism where original video-text pairs jointly provide visual and textual semantics, enabling structured learning of intrinsic spatiotemporal correspondences. Key advantages include: (i) Universality through supervision-free adaptation to diverse editing tasks, (ii) Unification of generation and editing applicable to most text(+image)-to-video model, and (iii) Efficiency via lightweight fine-tune that reduces tunable parameters by 92.67%. To enable systematic evaluation, we introduce OmniBench-99, a comprehensive benchmark spanning 99 videos across humans/animals, environments, and objects, comprising 4 editing types and 8 scenarios. Extensive experiments show UES enables models without inherent editing capability to perform powerful and universal editing while preserving or even enhancing their original generation performance.

Related papers

• FullDiT: Multi-Task Video Generative Foundation Model with Full Attention [37.776430879317765]
  FullDiT is a unified foundation model for video generation that seamlessly integrates multiple conditions via unified full-attention mechanisms. Experiments demonstrate that FullDiT achieves state-of-the-art results, highlighting the efficacy of full-attention in complex multi-task video generation.
  arXiv  Detail & Related papers  (2025-03-25T17:59:06Z)
• MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation [55.101611012677616]
  Diffusion-based text-to-image (T2I) models have demonstrated remarkable results in global video editing tasks. We present MAKIMA, a tuning-free MAE framework built upon pretrained T2I models for open-domain video editing.
  arXiv  Detail & Related papers  (2024-12-28T02:36:51Z)
• SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing [50.098005973600024]
  We propose a novel video generation and editing system powered by our Semantic Planning Agent (SPAgent) SPAgent bridges the gap between diverse user intents and the effective utilization of existing generative models. Experimental results demonstrate that the SPAgent effectively coordinates models to generate or edit videos.
  arXiv  Detail & Related papers  (2024-11-28T08:07:32Z)
• Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing [12.38953947065143]
  This work proposes an improved concept-augmented video editing approach that generates diverse and stable target videos flexibly. The framework involves concept-augmented textual inversion and a dual prior supervision mechanism. Comprehensive evaluations demonstrate that our approach generates more stable and lifelike videos, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-16T13:03:15Z)
• Zero-Shot Video Editing through Adaptive Sliding Score Distillation [51.57440923362033]
  This study proposes a novel paradigm of video-based score distillation, facilitating direct manipulation of original video content. We propose an Adaptive Sliding Score Distillation strategy, which incorporates both global and local video guidance to reduce the impact of editing errors.
  arXiv  Detail & Related papers  (2024-06-07T12:33:59Z)
• I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models [18.36472998650704]
  We introduce a novel and generic solution that extends the applicability of image editing tools to videos by propagating edits from a single frame to the entire video using a pre-trained image-to-video model. Our method, dubbed I2VEdit, adaptively preserves the visual and motion integrity of the source video depending on the extent of the edits.
  arXiv  Detail & Related papers  (2024-05-26T11:47:40Z)
• UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing [28.140945021777878]
  We present UniEdit, a tuning-free framework that supports both video motion and appearance editing. To realize motion editing while preserving source video content, we introduce auxiliary motion-reference and reconstruction branches. The obtained features are then injected into the main editing path via temporal and spatial self-attention layers.
  arXiv  Detail & Related papers  (2024-02-20T17:52:12Z)
• CCEdit: Creative and Controllable Video Editing via Diffusion Models [58.34886244442608]
  CCEdit is a versatile generative video editing framework based on diffusion models. Our approach employs a novel trident network structure that separates structure and appearance control. Our user studies compare CCEdit with eight state-of-the-art video editing methods.
  arXiv  Detail & Related papers  (2023-09-28T15:03:44Z)
• VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing [18.24307442582304]
  We introduce VidEdit, a novel method for zero-shot text-based video editing. Our experiments show that VidEdit outperforms state-of-the-art methods on DAVIS dataset.
  arXiv  Detail & Related papers  (2023-06-14T19:15:49Z)
• InstructVid2Vid: Controllable Video Editing with Natural Language Instructions [97.17047888215284]
  InstructVid2Vid is an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion.
  arXiv  Detail & Related papers  (2023-05-21T03:28:13Z)
• Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts [116.05656635044357]
  We propose a generic video editing framework called Make-A-Protagonist. Specifically, we leverage multiple experts to parse source video, target visual and textual clues, and propose a visual-textual-based video generation model. Results demonstrate the versatile and remarkable editing capabilities of Make-A-Protagonist.
  arXiv  Detail & Related papers  (2023-05-15T17:59:03Z)
• FateZero: Fusing Attentions for Zero-shot Text-based Video Editing [104.27329655124299]
  We propose FateZero, a zero-shot text-based editing method on real-world videos without per-prompt training or use-specific mask. Our method is the first one to show the ability of zero-shot text-driven video style and local attribute editing from the trained text-to-image model.
  arXiv  Detail & Related papers  (2023-03-16T17:51:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.