3D Gaussian Splatting (3DGS) has demonstrated superior quality in modeling 3D objects and scenes. However, generating 3DGS remains challenging due to their discrete, unstructured, and permutation-invariant nature. In this work, we present a simple yet effective method to overcome these challenges. We utilize spherical mapping to transform 3DGS into a structured 2D representation, termed UVGS. UVGS can be viewed as multi-channel images, with feature dimensions as a concatenation of Gaussian attributes such as position, scale, color, opacity, and rotation. We further find that these heterogeneous features can be compressed into a lower-dimensional (e.g., 3-channel) shared feature space using a carefully designed multi-branch network. The compressed UVGS can be treated as typical RGB images. Remarkably, we discover that typical VAEs trained with latent diffusion models can directly generalize to this new representation without additional training. Our novel representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly model 3DGS. Additionally, one can simply increase the 2D UV resolution to accommodate more Gaussians, making UVGS a scalable solution compared to typical 3D backbones. This approach immediately unlocks various novel generation applications of 3DGS by inherently utilizing the already developed superior 2D generation capabilities. In our experiments, we demonstrate various unconditional, conditional generation, and inpainting applications of 3DGS based on diffusion models, which were previously non-trivial.

We introduce EgoSonics, a method to generate semanti-cally meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent ego-centric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, mu-sic, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics ad-dresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode and process paired audio-video data to make them suitable for generation. The encoded data is then used to train a model that can generate an audio track that captures the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables generation of temporally-synchronized audio. Exten-sive evaluations and a comprehensive user study show that our model outperforms existing work in audio quality, and in our proposed synchronization evaluation method. Fur-thermore, we demonstrate downstream applications of our model in improving video summarization.

In recent years, there has been significant progress in 2D generative face models fueled by applications such as animation, synthetic data generation, and digital avatars. However, due to the absence of 3D information, these 2D models often struggle to accurately disentangle facial attributes like pose, expression, and illumination, limiting their editing capabilities. To address this limitation, this paper proposes a 3D controllable generative face model to produce high-quality albedo and precise 3D shapes by leveraging existing 2D generative models. By combining 2D face generative models with semantic face manipulation, this method enables editing of detailed 3D rendered faces. The proposed framework utilizes an alternating descent optimization approach over shape and albedo. Differentiable rendering is used to train high-quality shapes and albedo without 3D supervision. Moreover, this approach outperforms most state-of-the-art (SOTA) methods in the well-known NoW and REALY benchmarks for 3D face re construction. It also outperforms the SOTA reconstruction models in recovering rendered faces’ identities across novel poses. Additionally, the paper demonstrates direct control of expressions in 3D faces by exploiting latent space leading to text-based editing of 3D faces.

3D face modeling has been an active area of research in computer vision and computer graphics, fueling applications ranging from facial expression transfer in virtual avatars to synthetic data generation. Existing 3D deep learning generative models (e.g., VAE, GANs) allow generating compact face representations (both shape and texture) that can model non-linearities in the shape and appearance space (e.g., scatter effects, specularities,..). However, they lack the capability to control the generation of subtle expressions. This paper proposes a new 3D face generative model that can decouple identity and expression and provides granular control over expressions. In particular, we propose using a pair of supervised auto-encoder and generative adversarial networks to produce high-quality 3D faces, both in terms of appearance and shape. Experimental results in the generation of 3D faces learned with holistic expression labels, or Action Unit (AU) labels, show how we can decouple identity and expression; gaining fine-control over expressions while preserving identity.1

With the recent popularization of generative frameworks for producing photorealistic face images, we now have the ability to create a convincing graphical match for any particular individual. It is unrealistic, however, to rely solely on such generative methods to randomly produce the facial characteristics we are seeking. Instead, manipulation of facial attributes in the latent space, enabled by the InterFaceGAN framework, allows us to “tweak” these characteristics in the desired direction to improve the quality of the match. The challenge in this process is that attribute entanglement leads to a change of one feature having an undesirable impact on others. We explore several strategies to improve the results of these manipulations, and demonstrate how the automatic conditioning of attributes can be used to minimize the impact of such entanglement, and further, allow for improved control over complex (non-binary) attributes such as race or face shape.