Special Track on AI, the Arts and Creativity Papers (Guangzhou)

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation.
Achieving high quality and diversity in this process demands extensive, high-quality data, which are often scarce in available datasets. Most open-source datasets frequently suffer from issues like low-quality waveforms and low text-audio consistency, hindering the advancement of music generation models.
To address these challenges, we propose a novel quality-aware training paradigm for generating high-quality, high-musicality music from large-scale, quality-imbalanced datasets. Additionally, by leveraging unique properties in the latent space of musical signals, we adapt and implement a masked diffusion transformer (MDT) model for the TTM task, showcasing its capacity for quality control and enhanced musicality. Furthermore, we introduce a three-stage caption refinement approach to address low-quality captions’ issue. Experiments show state-of-the-art (SOTA) performance on benchmark datasets including MusicCaps and the Song-Describer Dataset with both objective and subjective metrics.
Demo audio samples are available at https://qa-mdt.github.io/, code and pretrained checkpoints are open-sourced at https://github.com/ivcylc/OpenMusic.

The rapid advancements in AI-generated content (AIGC) have led to extensive research and application of deep text-to-video (T2V) synthesis models, such as OpenAI’s Sora. These models typically rely on high-quality prompt-video pairs and detailed text prompts for model training in order to produce high-quality videos. To boost the effectiveness of Sora-like T2V models, we introduce VidPrompter, an innovative large multi-modal model supporting T2V applications with three key functionalities: (1) generating detailed prompts from raw videos, (2) enhancing prompts from videos grounded with short descriptions, and (3) refining simple user-provided prompts to elevate T2V video quality. We train VidPrompter using a hybrid multi-task paradigm and propose the hallucination-aware direct preference optimization (HDPO) technique to improve the multi-modal, multi-task prompt optimization process. Experiments on various tasks show our method surpasses strong baselines and other competitors.

Symbolic music generation aims to create musical notes, which can help users compose music, such as generating target instrument tracks based on provided source tracks. In practical scenarios where there’s a predefined ensemble of tracks and various composition needs, an efficient and effective generative model that can generate any target tracks based on the other tracks becomes crucial. However, previous efforts have fallen short in addressing this necessity due to limitations in their music representations and models. In this paper, we introduce a framework known as GETMusic, with “GET” standing for “GEnerate music Tracks.” This framework encompasses a novel music representation “GETScore” and a diffusion model “GETDiff.” GETScore represents musical notes as tokens and organizes tokens in a 2D structure, with tracks stacked vertically and progressing horizontally over time. At a training step, each track of a music piece is randomly selected as either the target or source. The training involves two processes: In the forward process, target tracks are corrupted by masking their tokens, while source tracks remain as the ground truth; in the denoising process, GETDiff is trained to predict the masked target tokens conditioning on the source tracks. Our proposed representation, coupled with the non-autoregressive generative model, empowers GETMusic to generate music with any arbitrary source-target track combinations.Our experiments demonstrate that the versatile GETMusic outperforms prior works proposed for certain specific composition tasks.

Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor achieves superior performance in this task and enables more personalized and creative image generation.

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text control, equivalently guiding different frame generations without frame-specific textual guidance. Thus, the model’s capacity to comprehend the temporal logic conveyed in prompts and generate videos with coherent motion is restricted. To tackle this limitation, we introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism with the well-designed Cross-frame Textual Guidance Module (CTGM). Specifically, CTGM incorporates the Temporal Information Injector (TII) and Temporal Affinity Refiner (TAR) at the beginning and end of cross-attention, respectively, to achieve frame-specific textual guidance. Firstly, TII injects frame-specific information from latent features into text conditions, thereby obtaining cross-frame textual conditions. Then, TAR refines the correlation matrix between cross-frame textual conditions and latent features along the time dimension. Extensive experiments comprising both quantitative and qualitative evaluations demonstrate the effectiveness of FancyVideo. Our approach achieves state-of-the-art T2V generation results on the EvalCrafter benchmark and facilitates the synthesis of dynamic and consistent videos. Note that the T2V process of FancyVideo essentially involves a text-to-image step followed by T+I2V. This means it also supports the generation of videos from user images, i.e., the image-to-video (I2V) task. A significant number of experiments have shown that its performance is also outstanding.

In AI-empowered poster design, content-aware layout generation is crucial for the on-image arrangement of visual-textual elements, e.g., logo, text, and underlay. To perceive the background images, existing work demanded a high parameter count that far exceeds the size of available training data, which has impeded the model’s real-time performance and generalization ability. To address these challenges, we proposed a patch-level data summarization and augmentation approach, vividly named Scan-and-Print. Specifically, the scan procedure selects only the patches suitable for placing element vertices to perform fine-grained perception efficiently. Then, the print procedure mixes up the patches and vertices across two image-layout pairs to synthesize over 100% new samples in each epoch while preserving their plausibility. Besides, to facilitate the vertex-level operations, a vertex-based layout representation is introduced. Extensive experimental results on widely used benchmarks demonstrated that Scan-and-Print can generate visually appealing layouts with state-of-the-art quality while dramatically reducing computational bottleneck by 95.2%. The project page is at https://thekinsley.github.io/Scan-and-Print/.

Video editing is a pivotal process for customizing video content according to user needs. However, existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-grained control for editing specific aspects in videos. To overcome these limitations, this paper introduces a novel approach named \emph{AdaptEdit}, which focuses on reference-based video editing that disentangles the editing process. It achieves this by first editing a reference image and then adaptively propagating its appearance across other frames to complete the video editing. While previous propagation methods, such as optical flow and the temporal modules of recent video generative models, struggle with object deformations and large motions, we propose an adaptive correspondence strategy that accurately transfers the appearance from the reference frame to the target frames by leveraging inter-frame semantic correspondences in the original video. By implementing a proxy-editing task to optimize hyperparameters for image token-level correspondence, our method effectively balances the need to maintain the target frame’s structure while preventing leakage of irrelevant appearance. To more accurately evaluate editing beyond the semantic-level consistency provided by CLIP-style models, we introduce a new dataset, PVA, which supports pixel-level evaluation. Our method outperforms the best-performing baseline with a clear PSNR improvement of 3.6 dB.

Precise 3D hand posture is essential for learning musical instruments. Reconstructing highly precise 3D hand gestures enables learners to correct and master proper techniques through 3D simulation and Extended Reality. However, exsiting methods typically rely on precisely calibrated multi-camera systems, which are not easily deployable in everyday environments. In this paper, we focus on calibration-free multi-view 3D hand reconstruction in unconstrained scenarios. Establishing correspondences between multi-view images is particularly challenging without camera extrinsics. To address this, we propose A^3-Net, a multi-level alignment framework that utilizes 3D structural representations with hierarchical geometric and explicit semantic information as alignment proxies, facilitating multi-view feature interaction in both 3D geometric space and 2D visual space. Specifically, we first perfrom global geometric alignment to map multi-view features into a canonical space. Subsequently, we aggregate information into predefined sparse and dense proxies to further integrate cross-view semantics through mutual interaction. Finnaly, we perfrom 2D alignment to align projected 2D visual features with 2D observations. Our method achieves state-of-the-art results in the multi-view 3D hand reconstruction task, demonstrating the effectiveness of our proposed framework.

As an essential movie promotional tool, trailers are designed to capture the audience’s interest through the skillful editing of key movie shots. Although some attempts have been made for automatic trailer generation, existing methods often rely on predefined rules or manual fine-grained annotations and fail to fully leverage the multi-modal information of movies, resulting in unsatisfactory trailer generation results. In this study, we introduce a weakly-supervised trailer generation method driven by multi-modal semantic consistency. Specifically, we design a multi-modal trailer generation framework that selects and sorts key movie shots based on input music and movie metadata (e.g., category tags and plot keywords) and adds narration to the generated trailer based on movie subtitles. We utilize two pseudo-scores derived from the proposed framework as labels and thus train the model under a weakly-supervised learning paradigm, ensuring trailerness consistency for key shot selection and emotion consistency for key shot sorting, respectively. As a result, we can learn the proposed model solely based on movie-trailer pairs without any fine-grained annotations. Both objective experimental results and subjective user studies demonstrate the superior performance of our method over previous works. The code is available at https://github.com/Dixin-Lab/MMSC.

This paper explores AI-mediated human-pet musical co-creation from an interdisciplinary perspective, leveraging recent advancements in animal-assisted therapy. These advancements have shown significant psychosocial benefits, especially in reducing anxiety and enhancing social engagement. Building on these findings, this study innovatively employs pet vocal timbres as ‘digital avatars’ to enhance emotional investment during the music creation process. We propose PetCoCre, a novel system that applies pet vocal timbres in three distinct character paradigms within AI music creation: (1) PetRhythm: using pet voices as rhythmic percussion through beat synchronization. (2) PetMelody: enabling pet voices to act as melodic instruments via pitch-shifting alignment. (3) PetVocalia: utilizing pet vocal timbres as the target timbre for SVC (Singing Voice Conversion), where the converted singing voice replaces the original singer’s voice, thus preserving the original semantic content.
Beyond these character paradigms, our technical innovation lies in proposing SaMoye, the first open-source, high-quality zero-shot SVC model that effectively overcomes existing methods’ zero-shot limitations by employing mixed speaker embeddings for timbre enhancement and leveraging a large-scale singing voice dataset.
In our experiments, we collected dog and cat vocalization data from pet stores and conducted experiments with 30 participants. Results demonstrate that the human-pet co-creation mode led to significant enhancements in pleasure and creative satisfaction compared to solo AI music generation, along with a significant reduction in participants’ anxiety levels.
Through collaborative art creation, this research pioneers new paradigms for animal-assisted therapeutic interventions and expands the boundaries of AI-assisted creative collaboration.