Related papers: Gaussian Masked Autoencoders
We present a novel approach for 3D indoor scene reconstruction that combines 3D Gaussian Splatting (3DGS) with mesh representations. We use meshes for the room layout of the indoor scene, such as walls, ceilings, and floors, while employing…
Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning. However, designing specific tasks for each type of graph data is often costly and lacks…
Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality.…
Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…
Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to…
Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a…
Recent advancements in foundation models have significantly impacted various fields, including natural language processing, computer vision, and multi-modal tasks. One area that stands to benefit greatly is Earth observation, where these…
Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS),…
Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view…
In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive…
3D Gaussian Splatting has recently emerged as an efficient solution for high-quality and real-time novel view synthesis. However, its capability for accurate surface reconstruction remains underexplored. Due to the discrete and unstructured…
Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic…
The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the organisation of the…
Recently, Gaussian Splatting (GS) has received a lot of attention in surface reconstruction. However, while 3D objects can be of complex and diverse shapes in the real world, existing GS-based methods only limitedly use a single type of…
Graph autoencoders (GAEs) and graph contrastive learning (GCL) are two major paradigms for self-supervised representation learning on graphs, yet they are often studied in isolation and treated as fundamentally different approaches. In this…
We present GaussExplorer, a framework for embodied exploration and reasoning built on 3D Gaussian Splatting (3DGS). While prior approaches to language-embedded 3DGS have made meaningful progress in aligning simple text queries with Gaussian…
Recent advances in dynamic scene reconstruction have significantly benefited from 3D Gaussian Splatting, yet existing methods show inconsistent performance across diverse scenes, indicating no single approach effectively handles all dynamic…
Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian. In this paper, we…