Flow matching models have emerged as a powerful method for generative modeling on domains like images or videos, and even on unstructured data like 3D point clouds. These models are commonly trained in two stages: first, a data compressor (i.e. a variational auto-encoder) is trained, and in a subsequent training stage a flow matching generative model is trained in the low-dimensional latent space of the data compressor. This two stage paradigm adds complexity to the overall training recipe and sets obstacles for unifying models across data domains, as specific data compressors are used for different data modalities. To this end, we introduce Ambient Space Flow Transformers (ASFT), a domain-agnostic approach to learn flow matching transformers in ambient space, sidestepping the requirement of training compressors and simplifying the training process. We introduce a conditionally independent point-wise training objective that enables ASFT to make predictions continuously in coordinate space. Our empirical results demonstrate that using general purpose transformer blocks, ASFT effectively handles different data modalities such as images and 3D point clouds, achieving strong performance in both domains and outperforming comparable approaches. ASFT is a promising step towards domain-agnostic flow matching generative models that can be trivially adopted in different data domains. Recent advances in generative modeling have enabled learning complex data distributions by combining both powerful architectures and training objectives. In particular, state-of-the-art approaches for image (Esser et al., 2024), video (Dai et al., 2023) or 3D point cloud (Vahdat et al., 2022) generation are based on the concept of iteratively transforming data into Gaussian noise. Diffusion models were originally proposed following this idea and pushing the quality of generated samples in many different domains, including images (Dai et al., 2023; Rombach et al., 2022), 3D point clouds (Luo & Hu, 2021), graphs (Hoogeboom et al., 2022) and video (Ho et al., 2022a). More recently, flow matching (Lipman et al., 2023) and stochastic interpolants (Ma et al., 2024) have been proposed as generalized formulations of the noising process, moving from stochastic gaussian diffusion processes to general paths connecting a base (e.g.

We consider the task of animating 3D facial geometry from speech signal. Existing works are primarily deterministic, focusing on learning a one-to-one mapping from speech signal to 3D face meshes on small datasets with limited speakers. While these models can achieve high-quality lip articulation for speakers in the training set, they are unable to capture the full and diverse distribution of 3D facial motions that accompany speech in the real world. Importantly, the relationship between speech and facial motion is one-to-many, containing both inter-speaker and intra-speaker variations and necessitating a probabilistic approach. In this paper, we identify and address key challenges that have so far limited the development of probabilistic models: lack of datasets and metrics that are suitable for training and evaluating them, as well as the difficulty of designing a model that generates diverse results while remaining faithful to a strong conditioning signal as speech. We first propose large-scale benchmark datasets and metrics suitable for probabilistic modeling. Then, we demonstrate a probabilistic model that achieves both diversity and fidelity to speech, outperforming other methods across the proposed benchmarks. Finally, we showcase useful applications of probabilistic models trained on these large-scale datasets: we can generate diverse speech-driven 3D facial motion that matches unseen speaker styles extracted from reference clips; and our synthetic meshes can be used to improve the performance of downstream audio-visual models.

Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing methods improve the quadratic complexity of attention, in most vision transformers, self-attention is not the major computation bottleneck, e.g., more than 80% of the computation is spent on fully-connected layers. To improve the computational complexity of all layers, we propose a novel token downsampling method, called Token Pooling, efficiently exploiting redundancies in the images and intermediate token representations. We show that, under mild assumptions, softmax-attention acts as a high-dimensional low-pass (smoothing) filter. Thus, its output contains redundancy that can be pruned to achieve a better trade-off between the computational cost and accuracy. Our new technique accurately approximates a set of tokens by minimizing the reconstruction error caused by downsampling. We solve this optimization problem via cost-efficient clustering. We rigorously analyze and compare to prior downsampling methods. Our experiments show that Token Pooling significantly improves the cost-accuracy trade-off over the state-of-the-art downsampling. Token Pooling is a simple and effective operator that can benefit many architectures. Applied to DeiT, it achieves the same ImageNet top-1 accuracy using 42% fewer computations.

To detect bias in face recognition networks, it can be useful to probe a network under test using samples in which only specific attributes vary in some controlled way. However, capturing a sufficiently large dataset with specific control over the attributes of interest is difficult. In this work, we describe a simulator that applies specific head pose and facial expression adjustments to images of previously unseen people. The simulator first fits a 3D morphable model to a provided image, applies the desired head pose and facial expression controls, then renders the model into an image. Next, a conditional Generative Adversarial Network (GAN) conditioned on the original image and the rendered morphable model is used to produce the image of the original person with the new facial expression and head pose. We call this conditional GAN -- MorphGAN. Images generated using MorphGAN conserve the identity of the person in the original image, and the provided control over head pose and facial expression allows test sets to be created to identify robustness issues of a facial recognition deep network with respect to pose and expression. Images generated by MorphGAN can also serve as data augmentation when training data are scarce. We show that by augmenting small datasets of faces with new poses and expressions improves the recognition performance by up to 9% depending on the augmentation and data scarcity.

Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. On one end of the spectrum, 3D face modeling methods provide parametric control but tend to generate unrealistic images, while on the other end, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. Trained GANs without pre-defined control, however, may entangle factors that are hard to undo later. To guarantee some disentanglement that provides us with desired kinds of control, we train our generative model conditioned on pre-defined control parameters. Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model. However, we found out that a naive conditioning on FLAME parameters yields rather unsatisfactory results. Instead we render out geometry and photo-metric details of the FLAME mesh and use these for conditioning instead. This gives us a generative 2D face model named GIF (Generative Interpretable Faces) that shares FLAME's parametric control. Given FLAME parameters for shape, pose, and expressions, parameters for appearance and lighting, and an additional style vector, GIF outputs photo-realistic face images. To evaluate how well GIF follows its conditioning and the impact of different design choices, we perform a perceptual study. The code and trained model are publicly available for research purposes at https://github.com/ParthaEth/GIF.