A Mamba Foundation Model for Time Series Forecasting

Time series foundation models have demonstrated strong performance in zero-shot learning, making them well-suited for predicting rapidly evolving patterns in real-world applications where relevant training data are scarce. However, most of these models rely on the Transformer architecture, which incurs quadratic complexity as input length increases. To address this, we introduce TSMamba, a linear-complexity foundation model for time series forecasting built on the Mamba architecture. The model captures temporal dependencies through both forward and backward Mamba encoders, achieving high prediction accuracy. To reduce reliance on large datasets and lower training costs, TSMamba employs a two-stage transfer learning process that leverages pretrained Mamba LLMs, allowing effective time series modeling with a moderate training set. In the first stage, the forward and backward backbones are optimized via patch-wise autoregressive prediction; in the second stage, the model trains a prediction head and refines other components for long-term forecasting. While the backbone assumes channel independence to manage varying channel numbers across datasets, a channel-wise compressed attention module is introduced to capture cross-channel dependencies during fine-tuning on specific multivariate datasets. Experiments show that TSMamba's zero-shot performance is comparable to state-of-the-art time series foundation models, despite using significantly less training data. It also achieves competitive or superior full-shot performance compared to task-specific prediction models. The code will be made publicly available.

Movie Gen: A Cast of Media Foundation Models

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.

Instance Tracking in 3D Scenes from Egocentric Videos

Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance by recalling 3D locations of objects of interest in the surrounding environment. This capability requires instance tracking in real-world 3D scenes from egocentric videos (IT3DEgo). We explore this problem by first introducing a new benchmark dataset, consisting of RGB and depth videos, per-frame camera pose, and instance-level annotations in both 2D camera and 3D world coordinates. We present an evaluation protocol which evaluates tracking performance in 3D coordinates with two settings for enrolling instances to track: (1) single-view online enrollment where an instance is specified on-the-fly based on the human wearer's interactions. and (2) multi-view pre-enrollment where images of an instance to be tracked are stored in memory ahead of time. To address IT3DEgo, we first re-purpose methods from relevant areas, e.g., single object tracking (SOT) -- running SOT methods to track instances in 2D frames and lifting them to 3D using camera pose and depth. We also present a simple method that leverages pretrained segmentation and detection models to generate proposals from RGB frames and match proposals with enrolled instance images. Perhaps surprisingly, our extensive experiments show that our method (with no finetuning) significantly outperforms SOT-based approaches. We conclude by arguing that the problem of egocentric instance tracking is made easier by leveraging camera pose and using a 3D allocentric (world) coordinate representation.

CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer

Reconstructing personalized animatable head avatars has significant implications in the fields of AR/VR. Existing methods for achieving explicit face control of 3D Morphable Models (3DMM) typically rely on multi-view images or videos of a single subject, making the reconstruction process complex. Additionally, the traditional rendering pipeline is time-consuming, limiting real-time animation possibilities. In this paper, we introduce CVTHead, a novel approach that generates controllable neural head avatars from a single reference image using point-based neural rendering. CVTHead considers the sparse vertices of mesh as the point set and employs the proposed Vertex-feature Transformer to learn local feature descriptors for each vertex. This enables the modeling of long-range dependencies among all the vertices. Experimental results on the VoxCeleb dataset demonstrate that CVTHead achieves comparable performance to state-of-the-art graphics-based methods. Moreover, it enables efficient rendering of novel human heads with various expressions, head poses, and camera views. These attributes can be explicitly controlled using the coefficients of 3DMMs, facilitating versatile and realistic animation in real-time scenarios.

Harmony World Models: Boosting Sample Efficiency for Model-based Reinforcement Learning

Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling. In this paper, through a dedicated empirical investigation, we gain a deeper understanding of the role each task plays in world models and uncover the overlooked potential of more efficient MBRL by harmonizing the interference between observation and reward modeling. Our key insight is that while prevalent approaches of explicit MBRL attempt to restore abundant details of the environment through observation models, it is difficult due to the environment's complexity and limited model capacity. On the other hand, reward models, while dominating in implicit MBRL and adept at learning task-centric dynamics, are inadequate for sample-efficient learning without richer learning signals. Capitalizing on these insights and discoveries, we propose a simple yet effective method, Harmony World Models (HarmonyWM), that introduces a lightweight harmonizer to maintain a dynamic equilibrium between the two tasks in world model learning. Our experiments on three visual control domains show that the base MBRL method equipped with HarmonyWM gains 10%-55% absolute performance boosts.

Light Field Diffusion for Single-View Novel View Synthesis

Single-view novel view synthesis, the task of generating images from new viewpoints based on a single reference image, is an important but challenging task in computer vision. Recently, Denoising Diffusion Probabilistic Model (DDPM) has become popular in this area due to its strong ability to generate high-fidelity images. However, current diffusion-based methods directly rely on camera pose matrices as viewing conditions, globally and implicitly introducing 3D constraints. These methods may suffer from inconsistency among generated images from different perspectives, especially in regions with intricate textures and structures. In this work, we present Light Field Diffusion (LFD), a conditional diffusion-based model for single-view novel view synthesis. Unlike previous methods that employ camera pose matrices, LFD transforms the camera view information into light field encoding and combines it with the reference image. This design introduces local pixel-wise constraints within the diffusion models, thereby encouraging better multi-view consistency. Experiments on several datasets show that our LFD can efficiently generate high-fidelity images and maintain better 3D consistency even in intricate regions. Our method can generate images with higher quality than NeRF-based models, and we obtain sample quality similar to other diffusion-based models but with only one-third of the model size.

Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstruction

We present Hybrid-CSR, a geometric deep-learning model that combines explicit and implicit shape representations for cortical surface reconstruction. Specifically, Hybrid-CSR begins with explicit deformations of template meshes to obtain coarsely reconstructed cortical surfaces, based on which the oriented point clouds are estimated for the subsequent differentiable poisson surface reconstruction. By doing so, our method unifies explicit (oriented point clouds) and implicit (indicator function) cortical surface reconstruction. Compared to explicit representation-based methods, our hybrid approach is more friendly to capture detailed structures, and when compared with implicit representation-based methods, our method can be topology aware because of end-to-end training with a mesh-based deformation module. In order to address topology defects, we propose a new topology correction pipeline that relies on optimization-based diffeomorphic surface registration. Experimental results on three brain datasets show that our approach surpasses existing implicit and explicit cortical surface reconstruction methods in numeric metrics in terms of accuracy, regularity, and consistency.

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

Unsupervised pre-training methods utilizing large and diverse datasets have achieved tremendous success across a range of domains. Recent work has investigated such unsupervised pre-training methods for model-based reinforcement learning (MBRL) but is limited to domain-specific or simulated data. In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of downstream visual control tasks. However, in-the-wild videos are complicated with various contextual factors, such as intricate backgrounds and textured appearance, which precludes a world model from extracting shared world knowledge to generalize better. To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly model both the context and dynamics to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes. Specifically, a contextualized extension of the latent dynamics model is elaborately realized by incorporating a context encoder to retain contextual information and empower the image decoder, which allows the latent dynamics model to concentrate on essential temporal variations. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample-efficiency of MBRL in various domains, including robotic manipulation, locomotion, and autonomous driving.

Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based methods in stereo super-resolution tasks. This can be attributed to two key factors: first, current single-image super-resolution transformers are unable to leverage the complementary stereo information during the process; second, the performance of transformers is typically reliant on sufficient data, which is absent in common stereo-image super-resolution algorithms. To address these issues, we propose a Hybrid Transformer and CNN Attention Network (HTCAN), which utilizes a transformer-based network for single-image enhancement and a CNN-based network for stereo information fusion. Furthermore, we employ a multi-patch training strategy and larger window sizes to activate more input pixels for super-resolution. We also revisit other advanced techniques, such as data augmentation, data ensemble, and model ensemble to reduce overfitting and data bias. Finally, our approach achieved a score of 23.90dB and emerged as the winner in Track 1 of the NTIRE 2023 Stereo Image Super-Resolution Challenge.