VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement
Recent text-to-video (T2V) diffusion models have demonstrated impressive generation capabilities across various domains. However, these models often generate videos that have misalignments with text prompts, especially when the prompts describe complex scenes with multiple objects and attributes. To address this, we introduce VideoRepair, a novel model-agnostic, training-free video refinement framework that automatically identifies fine-grained text-video misalignments and generates explicit spatial and textual feedback, enabling a T2V diffusion model to perform targeted, localized refinements. VideoRepair consists of four stages: In (1) video evaluation, we detect misalignments by generating fine-grained evaluation questions and answering those questions with MLLM. In (2) refinement planning, we identify accurately generated objects and then create localized prompts to refine other areas in the video. Next, in (3) region decomposition, we segment the correctly generated area using a combined grounding module. We regenerate the video by adjusting the misaligned regions while preserving the correct regions in (4) localized refinement. On two popular video generation benchmarks (EvalCrafter and T2V-CompBench), VideoRepair substantially outperforms recent baselines across various text-video alignment metrics. We provide a comprehensive analysis of VideoRepair components and qualitative examples.
Code (0)
등록된 구현이 없습니다.
Tasks
Text-to-Video GenerationVideo AlignmentVideo GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VideoGen-Eval: Agent-based System for Video Generation Evaluation
The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed ev…
DiversityVideo GenerationMJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation
Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, c…
BenchmarkingFairnessHallucinationMixture-of-Experts+1DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos
Currently, high-quality, synchronized audio is synthesized from video and optional text inputs using various multi-modal joint learning frameworks. However, the precise alignment between the visual and generated audio do…
Audio GenerationLarge Language ModelMM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning
Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches …
Video GenerationAligning Anime Video Generation with Human Feedback
Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with h…
Video Generation