KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation

Current audio-driven facial animation methods achieve impressive results for short videos but suffer from error accumulation and identity drift when extended to longer durations. Existing methods attempt to mitigate this through external spatial control, increasing long-term consistency but compromising the naturalness of motion. We propose KeyFace, a novel two-stage diffusion-based framework, to address these issues. In the first stage, keyframes are generated at a low frame rate, conditioned on audio input and an identity frame, to capture essential facial expressions and movements over extended periods of time. In the second stage, an interpolation model fills in the gaps between keyframes, ensuring smooth transitions and temporal coherence. To further enhance realism, we incorporate continuous emotion representations and handle a wide range of non-speech vocalizations (NSVs), such as laughter and sighs. We also introduce two new evaluation metrics for assessing lip synchronization and NSV generation. Experimental results show that KeyFace outperforms state-of-the-art methods in generating natural, coherent facial animations over extended durations, successfully encompassing NSVs and continuous emotions.

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models

Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional generative diffusion models. LoRA utilizes a small number of context examples to adapt the model to a specific domain, character, style, or concept. However, due to the limited data utilized during training, the fine-tuned model performance is often characterized by strong context bias and a low degree of variability in the generated images. To solve this issue, we introduce AutoLoRA, a novel guidance technique for diffusion models fine-tuned with the LoRA approach. Inspired by other guidance techniques, AutoLoRA searches for a trade-off between consistency in the domain represented by LoRA weights and sample diversity from the base conditional diffusion model. Moreover, we show that incorporating classifier-free guidance for both LoRA fine-tuned and base models leads to generating samples with higher diversity and better quality. The experimental results for several fine-tuned LoRA domains show superiority over existing guidance techniques on selected metrics.

Dimma: Semi-supervised Low Light Image Enhancement with Adaptive Dimming

Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations and limited access to photos with ground-truth lighting conditions. The latter is a crucial factor for supervised methods that achieve good results on paired datasets but do not handle out-of-domain data well. On the other hand, unsupervised methods, while able to generalize, often yield lower-quality enhancements. To fill this gap, we propose Dimma, a semi-supervised approach that aligns with any camera by utilizing a small set of image pairs to replicate scenes captured under extreme lighting conditions taken by that specific camera. We achieve that by introducing a convolutional mixture density network that generates distorted colors of the scene based on the illumination differences. Additionally, our approach enables accurate grading of the dimming factor, which provides a wide range of control and flexibility in adjusting the brightness levels during the low-light image enhancement process. To further improve the quality of our results, we introduce an architecture based on a conditional UNet. The lightness value provided by the user serves as the conditional input to generate images with the desired lightness. Our approach using only few image pairs achieves competitive results compared to fully supervised methods. Moreover, when trained on the full dataset, our model surpasses state-of-the-art methods in some metrics and closely approaches them in others.

Self-supervised adversarial masking for 3D point cloud representation learning

Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We introduce PointCAM, a novel adversarial method for learning a masking function for point clouds. Our model utilizes a self-distillation framework with an online tokenizer for 3D point clouds. Compared to previous techniques that optimize patch-level and object-level objectives, we postulate applying an auxiliary network that learns how to select masks instead of choosing them randomly. Our results show that the learned masking function achieves state-of-the-art or competitive performance on various downstream tasks. The source code is available at https://github.com/szacho/pointcam.

Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation

Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos. Recent developments in diffusion-based generative models allow for more realistic and stable data synthesis and their performance on image and video generation has surpassed that of other generative models. In this work, we present an autoregressive diffusion model that requires only one identity image and audio sequence to generate a video of a realistic talking human head. Our solution is capable of hallucinating head movements, facial expressions, such as blinks, and preserving a given background. We evaluate our model on two different datasets, achieving state-of-the-art results on both of them.

Continual learning on 3D point clouds with random compressed rehearsal

Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but effective processing of this type of data proves to be challenging. In the world of large, heavily-parameterized network architectures and continuously-streamed data, there is an increasing need for machine learning models that can be trained on additional data. Unfortunately, currently available models cannot fully leverage training on additional data without losing their past knowledge. Combating this phenomenon, called catastrophic forgetting, is one of the main objectives of continual learning. Continual learning for deep neural networks has been an active field of research, primarily in 2D computer vision, natural language processing, reinforcement learning, and robotics. However, in 3D computer vision, there are hardly any continual learning solutions specifically designed to take advantage of point cloud structure. This work proposes a novel neural network architecture capable of continual learning on 3D point cloud data. We utilize point cloud structure properties for preserving a heavily compressed set of past data. By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.

Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw

We present a number of low-resource approaches to the tasks of the Zero Resource Speech Challenge 2021. We build on the unsupervised representations of speech proposed by the organizers as a baseline, derived from CPC and clustered with the k-means algorithm. We demonstrate that simple methods of refining those representations can narrow the gap, or even improve upon the solutions which use a high computational budget. The results lead to the conclusion that the CPC-derived representations are still too noisy for training language models, but stable enough for simpler forms of pattern matching and retrieval.

Aligned Contrastive Predictive Coding

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations. Rather than producing individual predictions for each of the future representations, the model emits a sequence of predictions shorter than that of the upcoming representations to which they will be aligned. In this way, the prediction network solves a simpler task of predicting the next symbols, but not their exact timing, while the encoding network is trained to produce piece-wise constant latent codes. We evaluate the model on a speech coding task and demonstrate that the proposed Aligned Contrastive Predictive Coding (ACPC) leads to higher linear phone prediction accuracy and lower ABX error rates, while being slightly faster to train due to the reduced number of prediction heads.

Representing Point Clouds with Generative Conditional Invertible Flow Networks

In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the number of points and their ordering within a cloud is not important as all points are drawn from the proximity of the object boundary. We postulate to represent each cloud as a parameterized probability distribution defined by a generative neural network. Once trained, such a model provides a natural framework for point cloud manipulation operations, such as aligning a new cloud into a default spatial orientation. To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector. We show that these embedding vectors capture semantic relationships between objects. Our method leverages generative invertible flow networks to learn embeddings as well as to generate point clouds. Thanks to this formulation and contrary to similar approaches, we are able to train our model in an end-to-end fashion. As a result, our model offers competitive or superior quantitative results on benchmark datasets, while enabling unprecedented capabilities to perform cloud manipulation tasks, such as point cloud registration and regeneration, by a generative network.

Conditional Invertible Flow for Point Cloud Generation

This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a probability density in 3D space that is modeled using a cloud-specific neural network. To capture the similarity between point clouds we rely on parameter sharing among networks, with each cloud having only a small embedding vector that defines it. We use invertible flows networks to generate the individual point clouds, and to regularize the embedding vectors. We evaluate the generative capabilities of the model both in qualitative and quantitative manner.