CVPR 2025 Papers

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark.We will release our pretrained models and the VinTAGe-Bench dataset to facilitate future research in this exciting field.

Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions.

Text-to-image (T2I) diffusion models have revolutionized visual content creation, but extending these capabilities to text-to-video (T2V) generation remains a challenge, particularly in preserving temporal consistency. Existing methods that aim to improve consistency often cause trade-offs such as reduced imaging quality and impractical computational time. To address these issues we introduce VideoGuide, a novel framework that enhances the temporal consistency of pretrained T2V models without the need for additional training or fine-tuning. Instead, VideoGuide leverages any pretrained video diffusion model (VDM) or itself as a guide during the early stages of inference, improving temporal quality by interpolating the guiding model's denoised samples into the sampling model's denoising process. The proposed method brings about significant improvement in temporal consistency and image fidelity, providing a cost-effective and practical solution that synergizes the strengths of various video diffusion models. Furthermore, we demonstrate prior distillation, revealing that base models can achieve enhanced text coherence by utilizing the superior data prior of the guiding model through the proposed method. Project Page: https://dohunlee1.github.io/videoguide.github.io/

Video super-resolution (VSR) models achieve temporal consistency but often produce blurrier results than their image-based counterparts due to limited generative capacity. This prompts the question: can we adapt a generative image upsampler for VSR while preserving temporal consistency? We introduce VideoGigaGAN, a new generative VSR model that combines high-frequency detail with temporal stability, building on the large-scale GigaGAN image upsampler. Simple adaptations of GigaGAN for VSR led to flickering issues, so we propose techniques to enhance temporal consistency. We validate the effectiveness of VideoGigaGAN by comparing it with state-of-the-art VSR models on public datasets and showcasing video results with 8x upsampling.

Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods primarily rely on T2I models, which inherently lack temporal-coherence generative ability, often resulting in inferior editing results. In this paper, we attribute the failure of the typical editing paradigm to: 1) Tightly Spatial-temporal Coupling. The vanilla pivotal-based inversion strategy struggles to disentangle spatial-temporal information in the video diffusion model; 2) Complicated Spatial-temporal Layout. The vanilla cross-attention control strategy is deficient in preserving the unedited content. To address these limitations, we propose a spatial-temporal decoupled guidance (STDG) and multi-frame null-text optimization strategy to provide pivotal temporal cues for more precise pivotal inversion. Furthermore, we introduce a self-attention control strategy to maintain higher fidelity for precise partial content editing. Experimental results demonstrate that our method (termed VideoDirector) effectively harnesses the powerful temporal generation capabilities of T2V models, producing edited videos with state-of-the-art performance in accuracy, motion smoothness, realism, and fidelity to unedited content.

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user preferences, highlighting the need for preference alignment on pre-trained models. Although Direct Preference Optimization (DPO) has demonstrated significant improvements in language and image generation, we pioneer its adaptation to video diffusion models and propose a VideoDPO pipeline by making several key adjustments. Unlike previous image alignment methods that focus solely on either (i) visual quality or (ii) semantic alignment between text and videos, we comprehensively consider both dimensions and construct a preference score accordingly, which we term the OmniScore. We design a pipeline to automatically collect preference pair data based on the proposed OmniScore and discover that re-weighting these pairs based on the score significantly impacts overall preference alignment. Our experiments demonstrate substantial improvements in both visual quality and semantic alignment, ensuring that no preference aspect is neglected. Code and data will be shared at https://videodpo.github.io/.

We introduce VideoComp, a benchmark and learning framework for advancing video-text compositionality understanding, aimed at improving vision-language models (VLMs) in fine-grained temporal alignment. Unlike existing benchmarks focused on static image-text compositionality or isolated single-event videos, our benchmark targets alignment in continuous multi-event videos. Leveraging video-text datasets with temporally localized event captions (e.g. ActivityNet-Captions, YouCook2), we construct two compositional benchmarks, ActivityNet-Comp and YouCook2-Comp. We create challenging negative samples with subtle temporal disruptions such as reordering, action word replacement, partial captioning, and combined disruptions. These benchmarks comprehensively test models' compositional sensitivity across extended, cohesive video-text sequences. To improve model performance, we propose a hierarchical pairwise preference loss that strengthens alignment with temporally accurate pairs and gradually penalizes increasingly disrupted ones, encouraging fine-grained compositional learning. To mitigate the limited availability of densely annotated video data, we introduce a pretraining strategy that concatenates short video-caption pairs to simulate multi-event sequences. We evaluate video-text foundational models and large multimodal models (LMMs) on our benchmark, identifying both strengths and areas for improvement in compositionality. Overall, our work provides a comprehensive framework for evaluating and enhancing model capabilities in achieving fine-grained, temporally coherent video-text alignment.

Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce *MultiFoley*, a model designed for video-guided sound generation that supports multimodal conditioning through text, audio, and video. Given a silent video and a text prompt, MultiFoley allows users to create clean sounds (e.g., skateboard wheels spinning without wind noise) or more whimsical sounds (e.g., making a lion's roar sound like a cat's meow).MultiFoley also allows users to choose reference audio from sound effects (SFX) libraries or partial videos for conditioning. A key novelty of our model lies in its joint training on both internet video datasets with low-quality audio and professional SFX recordings, enabling high-quality, full-bandwidth (48kHz) audio generation.Through automated evaluations and human studies, we demonstrate that *MultiFoley* successfully generates synchronized high-quality sounds across varied conditional inputs and outperforms existing methods.

In this work, we tackle the problem of text-to-video retrieval (T2VR). Inspired by the success of late interaction techniques in text-document, text-image, and text-video retrieval, our approach, Video-ColBERT, introduces a simple and efficient mechanism for fine-grained similarity assessment between queries and videos. Video-ColBERT is built upon 3 main components: a fine-grained spatial and temporal token-wise interaction, query and visual expansions, and a dual sigmoid loss during training. We find that this interaction and training paradigm leads to strong individual, yet compatible, representations for encoding video content. These representations lead to increases in performance on common text-to-video retrieval benchmarks compared to other bi-encoder methods.

Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories: traditional benchmarks, which use metrics and embeddings to evaluate generated video quality across multiple dimensions but often lack alignment with human judgments; and large language model (LLM)-based benchmarks, though capable of human-like reasoning, are constrained by a limited understanding of video quality metrics and cross-modal consistency.To address these challenges and establish a benchmark that better aligns with human preferences, this paper introduces Video-Bench, a comprehensive benchmark featuring a rich prompt suite and extensive evaluation dimensions. This benchmark represents the first attempt to systematically leverage MLLMs across all dimensions relevant to video generation assessment in generative models. By incorporating few-shot scoring and chain-of-query techniques, Video-Bench provides a structured, scalable approach to generated video evaluation. Experimental results demonstrate that MLLMs achieve superior alignment with human preferences across all dimensions. Moreover, in instances where our framework's assessments diverge from human evaluations, it consistently offers more objective and accurate insights, suggesting an even greater potential advantage over traditional human judgment.

The exponential increase in video content poses significant challenges in terms of efficient navigation, search, and retrieval, thus requiring advanced video summarization techniques. Existing video summarization methods, which heavily rely on visual features and temporal dynamics, often fail to capture the semantics of video content, resulting in incomplete or incoherent summaries. To tackle the challenge, we propose a new video summarization framework that leverages the capabilities of recent Large Language Models (LLMs), expecting that the knowledge learned from massive data enables LLMs to evaluate video frames in a manner that better aligns with diverse semantics and human judgments, effectively addressing the inherent subjectivity in defining keyframes. Our method, dubbed LLM-based Video Summarization (LLMVS), translates video frames into a sequence of captions using a Muti-modal Large Language Model (M-LLM) and then assesses the importance of each frame using an LLM, based on the captions in its local context. These local importance scores are refined through a global attention mechanism in the entire context of video captions, ensuring that our summaries effectively reflect both the details and the overarching narrative. Our experimental results demonstrate the superiority of the proposed method over existing ones in standard benchmarks, highlighting the potential of LLMs in the processing of multimedia content.

The development of self-supervised video-language models based on mask learning has significantly advanced downstream video tasks. These models leverage masked reconstruction to facilitate joint learning of visual and linguistic information. However, recent study reveals that reconstructing image features yields superior downstream performance compared to video feature reconstruction. We hypothesize that this performance gap stems from the way how masking strategies influence the model's attention to temporal dynamics. To validate this hypothesis, we performed two sets of experiments that demonstrate that alignment between the masked target and the reconstruction target is crucial for self-supervised video-language learning. Based on these findings, we propose a spatio-temporal masking strategy (STM) for video-language model pretraining that operates across adjacent frames, and a decoder leverages semantic information to enhance the spatio-temporal representations of masked tokens. Thanks to the combination of masking strategy and reconstruction decoder, STM enforces the model to learn spatio-temporal feature representation comprehensively. Experiments in three video understanding downstream tasks validate the superiority of our method.

Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal inconsistency in videos, hindering its practical applications. Various methods have been proposed to alleviate this issue by leveraging video generation models or introducing priors from optical flow and camera poses. Nonetheless, these methods are only applicable to short videos (10 seconds) and require a trade-off between quality and computational efficiency. We propose Video Depth Anything for high-quality, consistent depth estimation in super-long videos (over several minutes) without sacrificing efficiency. We base our model on Depth Anything V2 and replace its head with an efficient spatial-temporal head. We design a straightforward yet effective temporal consistency loss by constraining the temporal depth gradient, eliminating the need for additional geometric priors. The model is trained on a joint dataset of video depth and unlabeled images, similar to Depth Anything V2. Moreover, a novel key-frame-based strategy is developed for long video inference. Experiments show that our model can be applied to arbitrarily long videos without compromising quality, consistency, or generalization ability. Comprehensive evaluations on multiple video benchmarks demonstrate that our approach sets a new state-of-the-art in zero-shot video depth estimation. We offer models of different scales to support a range of scenarios, with our smallest model capable of real-time performance at 30 FPS.

We investigate complex video question answering via chain-of-evidence reasoning --- identifying sequences of temporal spans from multiple relevant parts of the video, together with visual evidence within them.Existing models struggle with multi-step reasoning as they uniformly sample a fixed number of frames, which can miss critical evidence distributed nonuniformly throughout the video. Moreover, they lack the ability to temporally localize such evidence in the broader context of the full video, which is required for answering complex questions. We propose a framework to enhance existing VideoQA datasets with evidence reasoning chains, automatically constructed by searching for optimal intervals of interest in the video with supporting evidence, that maximizes the likelihood of answering a given question.We train our model (ViTED) to generate these evidence chains directly, enabling it to both localize evidence windows as well as perform multi-step reasoning across them in long-form video content.We show the value of our evidence-distilled models on a suite of long video QA benchmarks where we outperform state-of-the-art approaches that lack evidence reasoning capabilities.

We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment the diffusion transformer backbone with the sketch attention to interpret and inject fine-grained sketch semantics. A sketch-aware encoder ensures that repainted results are aligned with the provided sketch sequence. Additionally, we contribute the VireSet, a dataset with detailed annotations tailored for training and evaluating video instance editing methods. Experimental results demonstrate the effectiveness of VIRES, which outperforms state-of-the-art methods in visual quality, temporal consistency, condition alignment, and human ratings. The code, dataset and pretrained models are available at: https://hjzheng.net/projects/VIRES.

Recently, text-driven video editing methods that optimize target latent representations have garnered significant attention and demonstrated promising results. However, these methods rely on self-supervised objectives to compute the gradients needed for updating latent representations, which inevitably introduces gradient noise, compromising content generation quality. Additionally, it is challenging to determine the optimal stopping point for the editing process, making it difficult to achieve an optimal solution for the latent representation. To address these issues, we propose a unified gradient-latent purification framework that collects gradient and latent information across different stages to identify effective and concordant update directions. We design a local coordinate system construction method based on feature decomposition, enabling short-term gradients and final-stage latents to be reprojected onto new axes. Then, we employ tailored coefficient regularization terms to effectively aggregate the decomposed information. Additionally, a temporal smoothing axis extension strategy is developed to enhance the temporal coherence of the generated content. Extensive experiments demonstrate that our proposed method outperforms state-of-the-art methods across various editing tasks, delivering superior editing performance. Project page is available in https://unity-in-diversity-editing.github.io.