arXiv subjects

Yuki Mitsufuji

Publications and source records attributed to Yuki Mitsufuji.

At least 127 records · Page 7Linked to original sources

arXiv2025

Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification

Audio fingerprinting (AFP) allows the identification of unknown audio content by extracting compact representations, termed audio fingerprints, that are designed to remain robust against common audio degradations. Neural AFP methods often employ metric learning, where representation quality is influenced by the nature of the supervision and the utilized loss function. However, recent work unrealistically simulates real-life audio degradation during training, resulting in sub-optimal supervision. Additionally, although several modern metric learning approaches have been proposed, current neural AFP methods continue to rely on the NT-Xent loss without exploring the recent advances or classical alternatives. In this work, we propose a series of best practices to enhance the self-supervision by leveraging musical signal properties and realistic room acoustics. We then present the first systematic evaluation of various metric learning approaches in the context of AFP, demonstrating that a self-supervised adaptation of the triplet loss yields superior performance. Our results also reveal that training with multiple positive samples per anchor has critically different effects across loss functions. Our approach is built upon these insights and achieves state-of-the-art performance on both a large, synthetically degraded dataset and a real-world dataset recorded using microphones in diverse music venues.

cs.SD↗

arXiv2025

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view video data for training. Traditional reconstruction methods struggle with extreme trajectory changes, and existing generative models for dynamic novel view synthesis cannot handle in-the-wild videos. Our approach consists of two steps: estimating temporally consistent geometry, and generative rendering guided by this geometry. By integrating geometric priors, the generative model focuses on synthesizing realistic details where the estimated geometry is uncertain. We eliminate the need for extensive 4D training data through a factorized fine-tuning framework that separately trains spatial and temporal components using multi-view image and video data. Our method outperforms baselines in producing plausible videos from novel camera trajectories, especially in extreme extrapolation scenarios on real-world footage.

cs.CV↗

arXiv2025

VCT: Training Consistency Models with Variational Noise Coupling

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training dynamics. We propose Variational Consistency Training (VCT), a flexible and effective framework compatible with various forward kernels, including those in flow matching. Its key innovation is a learned noise-data coupling scheme inspired by Variational Autoencoders, where a data-dependent encoder models noise emission. This enables VCT to adaptively learn noise-todata pairings, reducing training variance relative to the fixed, unsorted pairings in classical CT. Experiments on multiple image datasets demonstrate significant improvements: our method surpasses baselines, achieves state-of-the-art FID among non-distillation CT approaches on CIFAR-10, and matches SoTA performance on ImageNet 64 x 64 with only two sampling steps. Code is available at https://github.com/sony/vct.

cs.LG↗

arXiv2025

Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity

Recently, Generative Adversarial Networks (GANs) have been successfully scaled to billion-scale large text-to-image datasets. However, training such models entails a high training cost, limiting some applications and research usage. To reduce the cost, one promising direction is the incorporation of pre-trained models. The existing method of utilizing pre-trained models for a generator significantly reduced the training cost compared with the other large-scale GANs, but we found the model loses the diversity of generation for a given prompt by a large margin. To build an efficient and high-fidelity text-to-image GAN without compromise, we propose to use two specialized discriminators with Slicing Adversarial Networks (SANs) adapted for text-to-image tasks. Our proposed model, called SCAD, shows a notable enhancement in diversity for a given prompt with better sample fidelity. We also propose to use a metric called Per-Prompt Diversity (PPD) to evaluate the diversity of text-to-image models quantitatively. SCAD achieved a zero-shot FID competitive with the latest large-scale GANs at two orders of magnitude less training cost.

cs.CV↗

arXiv2025

A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?

We introduce the Robust Audio Watermarking Benchmark (RAW-Bench), a benchmark for evaluating deep learning-based audio watermarking methods with standardized and systematic comparisons. To simulate real-world usage, we introduce a comprehensive audio attack pipeline with various distortions such as compression, background noise, and reverberation, along with a diverse test dataset including speech, environmental sounds, and music recordings. Evaluating four existing watermarking methods on RAW-bench reveals two main insights: (i) neural compression techniques pose the most significant challenge, even when algorithms are trained with such compressions; and (ii) training with audio attacks generally improves robustness, although it is insufficient in some cases. Furthermore, we find that specific distortions, such as polarity inversion, time stretching, or reverb, seriously affect certain methods. The evaluation framework is accessible at github.com/SonyResearch/raw_bench.

cs.SD↗

arXiv2025

Music Foundation Model as Generic Booster for Music Downstream Tasks

We demonstrate the efficacy of using intermediate representations from a single foundation model to enhance various music downstream tasks. We introduce SoniDo, a music foundation model (MFM) designed to extract hierarchical features from target music samples. By leveraging hierarchical intermediate features, SoniDo constrains the information granularity, leading to improved performance across various downstream tasks including both understanding and generative tasks. We specifically evaluated this approach on representative tasks such as music tagging, music transcription, music source separation, and music mixing. Our results reveal that the features extracted from foundation models provide valuable enhancements in training downstream task models. This highlights the capability of using features extracted from music foundation models as a booster for downstream tasks. Our approach not only benefits existing task-specific models but also supports music downstream tasks constrained by data scarcity. This paves the way for more effective and accessible music processing solutions.

cs.SD↗

arXiv2025

Supervised contrastive learning from weakly-labeled audio segments for musical version matching

Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match musical versions at the track level (e.g., whole song). However, most applications require to match them at the segment level (e.g., 20s chunks). In addition, existing approaches resort to classification and triplet losses, disregarding more recent losses that could bring meaningful improvements. In this paper, we propose a method to learn from weakly annotated segments, together with a contrastive loss variant that outperforms well-studied alternatives. The former is based on pairwise segment distance reductions, while the latter modifies an existing loss following decoupling, hyper-parameter, and geometric considerations. With these two elements, we do not only achieve state-of-the-art results in the standard track-level evaluation, but we also obtain a breakthrough performance in a segment-level evaluation. We believe that, due to the generality of the challenges addressed here, the proposed methods may find utility in domains beyond audio or musical version matching.

cs.SD↗

arXiv2025

Dyadic Mamba: Long-term Dyadic Human Motion Synthesis

Generating realistic dyadic human motion from text descriptions presents significant challenges, particularly for extended interactions that exceed typical training sequence lengths. While recent transformer-based approaches have shown promising results for short-term dyadic motion synthesis, they struggle with longer sequences due to inherent limitations in positional encoding schemes. In this paper, we introduce Dyadic Mamba, a novel approach that leverages State-Space Models (SSMs) to generate high-quality dyadic human motion of arbitrary length. Our method employs a simple yet effective architecture that facilitates information flow between individual motion sequences through concatenation, eliminating the need for complex cross-attention mechanisms. We demonstrate that Dyadic Mamba achieves competitive performance on standard short-term benchmarks while significantly outperforming transformer-based approaches on longer sequences. Additionally, we propose a new benchmark for evaluating long-term motion synthesis quality, providing a standardized framework for future research. Our results demonstrate that SSM-based architectures offer a promising direction for addressing the challenging task of long-term dyadic human motion synthesis from text descriptions.

cs.CV↗

arXiv2025

Distillation of Discrete Diffusion through Dimensional Correlations

Diffusion models have demonstrated exceptional performances in various fields of generative modeling, but suffer from slow sampling speed due to their iterative nature. While this issue is being addressed in continuous domains, discrete diffusion models face unique challenges, particularly in capturing dependencies between elements (e.g., pixel relationships in image, sequential dependencies in language) mainly due to the computational cost of processing high-dimensional joint distributions. In this paper, (i) we propose "mixture" models for discrete diffusion that are capable of treating dimensional correlations while remaining scalable, and (ii) we provide a set of loss functions for distilling the iterations of existing models. Two primary theoretical insights underpin our approach: First, conventional models with element-wise independence can well approximate the data distribution, but essentially require {\it many sampling steps}. Second, our loss functions enable the mixture models to distill such many-step conventional models into just a few steps by learning the dimensional correlations. Our experimental results show the effectiveness of the proposed method in distilling pretrained discrete diffusion models across image and language domains. The code used in the paper is available at https://github.com/sony/di4c .

cs.LG↗

arXiv2025

Variable Bitrate Residual Vector Quantization for Audio Coding

Recent state-of-the-art neural audio compression models have progressively adopted residual vector quantization (RVQ). Despite this success, these models employ a fixed number of codebooks per frame, which can be suboptimal in terms of rate-distortion tradeoff, particularly in scenarios with simple input audio, such as silence. To address this limitation, we propose variable bitrate RVQ (VRVQ) for audio codecs, which allows for more efficient coding by adapting the number of codebooks used per frame. Furthermore, we propose a gradient estimation method for the non-differentiable masking operation that transforms from the importance map to the binary importance mask, improving model training via a straight-through estimator. We demonstrate that the proposed training framework achieves superior results compared to the baseline method and shows further improvement when applied to the current state-of-the-art codec.

cs.SD↗

arXiv2025

Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image

Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern is often considered hard to remove and forge into unrelated images. In this paper, we propose a black-box adversarial attack without presuming access to the diffusion model weights. Our attack uses only a single watermarked example and is based on a simple observation: there is a many-to-one mapping between images and initial noises. There are regions in the clean image latent space pertaining to each watermark that get mapped to the same initial noise when inverted. Based on this intuition, we propose an adversarial attack to forge the watermark by introducing perturbations to the images such that we can enter the region of watermarked images. We show that we can also apply a similar approach for watermark removal by learning perturbations to exit this region. We report results on multiple watermarking schemes (Tree-Ring, RingID, WIND, and Gaussian Shading) across two diffusion models (SDv1.4 and SDv2.0). Our results demonstrate the effectiveness of the attack and expose vulnerabilities in the watermarking methods, motivating future research on improving them.

cs.CV↗

arXiv2025

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training

In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and editing the generated motions according to control signals, such as the start-end positions and the pelvis trajectory. In this paper, we propose MoLA, which provides fast, high-quality, variable-length motion generation and can also deal with multiple editing tasks in a single framework. Our approach revisits the motion representation used as inputs and outputs in the model, incorporating an activation variable to enable variable-length motion generation. Additionally, we integrate a variational autoencoder and a latent diffusion model, further enhanced through adversarial training, to achieve high-quality and fast generation. Moreover, we apply a training-free guided generation framework to achieve various editing tasks with motion control inputs. We quantitatively show the effectiveness of adversarial learning in text-to-motion generation, and demonstrate the applicability of our editing framework to multiple editing tasks in the motion domain.

cs.CV↗

arXiv2025

A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.

cs.LG↗

arXiv2025

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples. Additionally, we improve audio-visual synchrony with a conditional synchronization module that aligns video conditions with audio latents at the frame level. Trained with a flow matching objective, MMAudio achieves new video-to-audio state-of-the-art among public models in terms of audio quality, semantic alignment, and audio-visual synchronization, while having a low inference time (1.23s to generate an 8s clip) and just 157M parameters. MMAudio also achieves surprisingly competitive performance in text-to-audio generation, showing that joint training does not hinder single-modality performance. Code and demo are available at: https://hkchengrex.github.io/MMAudio

cs.CV↗

arXiv2025

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

Visual narrative generation transforms textual narratives into sequences of images illustrating the content of the text. However, generating visual narratives that are faithful to the input text and self-consistent across generated images remains an open challenge, due to the lack of knowledge constraints used for planning the stories. In this work, we propose a new benchmark, VinaBench, to address this challenge. Our benchmark annotates the underlying commonsense and discourse constraints in visual narrative samples, offering systematic scaffolds for learning the implicit strategies of visual storytelling. Based on the incorporated narrative constraints, we further propose novel metrics to closely evaluate the consistency of generated narrative images and the alignment of generations with the input textual narrative. Our results across three generative vision models demonstrate that learning with VinaBench's knowledge constraints effectively improves the faithfulness and cohesion of generated visual narratives.

cs.CV↗

arXiv2025

Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion methods rely on fixed pretrained embeddings, limiting the benefits of joint training with the diffusion model. While jointly learning the embedding (via reconstruction loss) and the latent diffusion model (via score matching loss) could enhance performance, end-to-end training risks embedding collapse, degrading generation quality. To mitigate this issue, we introduce VQ-LCMD, a continuous-space latent diffusion framework within the embedding space that stabilizes training. VQ-LCMD uses a novel training objective combining the joint embedding-diffusion variational lower bound with a consistency-matching (CM) loss, alongside a shifted cosine noise schedule and random dropping strategy. Experiments on several benchmarks show that the proposed VQ-LCMD yields superior results on FFHQ, LSUN Churches, and LSUN Bedrooms compared to discrete-state latent diffusion models. In particular, VQ-LCMD achieves an FID of 6.81 for class-conditional image generation on ImageNet with 50 steps.

cs.LG↗

arXiv2025

Aligning Text-to-Music Evaluation with Human Preferences

Despite significant recent advances in generative acoustic text-to-music (TTM) modeling, robust evaluation of these models lags behind, relying in particular on the popular Fréchet Audio Distance (FAD). In this work, we rigorously study the design space of reference-based divergence metrics for evaluating TTM models through (1) designing four synthetic meta-evaluations to measure sensitivity to particular musical desiderata, and (2) collecting and evaluating on MusicPrefs, the first open-source dataset of human preferences for TTM systems. We find that not only is the standard FAD setup inconsistent on both synthetic and human preference data, but that nearly all existing metrics fail to effectively capture desiderata, and are only weakly correlated with human perception. We propose a new metric, the MAUVE Audio Divergence (MAD), computed on representations from a self-supervised audio embedding model. We find that this metric effectively captures diverse musical desiderata (average rank correlation 0.84 for MAD vs. 0.49 for FAD and also correlates more strongly with MusicPrefs (0.62 vs. 0.14).

cs.SD↗

arXiv2025

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization

Diffusion models are prone to exactly reproduce images from the training data. This exact reproduction of the training data is concerning as it can lead to copyright infringement and/or leakage of privacy-sensitive information. In this paper, we present a novel perspective on the memorization phenomenon and propose a simple yet effective approach to mitigate it. We argue that memorization occurs because of an attraction basin in the denoising process which steers the diffusion trajectory towards a memorized image. However, this can be mitigated by guiding the diffusion trajectory away from the attraction basin by not applying classifier-free guidance until an ideal transition point occurs from which classifier-free guidance is applied. This leads to the generation of non-memorized images that are high in image quality and well-aligned with the conditioning mechanism. To further improve on this, we present a new guidance technique, opposite guidance, that escapes the attraction basin sooner in the denoising process. We demonstrate the existence of attraction basins in various scenarios in which memorization occurs, and we show that our proposed approach successfully mitigates memorization.

cs.CV↗