Related papers: OctAttention: Octree-Based Large-Scale Contexts Mo…
Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial…
Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since…
We introduce a deep recursive octree network for the compression of 3D voxel data. Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network. We show results for compressing 32, 64 and…
Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress…
Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes. However, it is a challenging problem to compress sparse, unstructured, and…
The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while…
We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…
The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry…
The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as…
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the…
Emerging event cameras acquire visual information by detecting time domain brightness changes asynchronously at the pixel level and, unlike conventional cameras, are able to provide high temporal resolution, very high dynamic range, low…
In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study…
Compressing massive LiDAR point clouds in real-time is critical to autonomous machines such as drones and self-driving cars. While most of the recent prior work has focused on compressing individual point cloud frames, this paper proposes a…
Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention. However, many modern applications-from multi-turn dialogue to high-resolution vision-require contexts spanning tens of thousands…
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…
We study 3D point cloud attribute compression using a volumetric approach: given a target volumetric attribute function $f : \mathbb{R}^3 \rightarrow \mathbb{R}$, we quantize and encode parameter vector $\theta$ that characterizes $f$ at…
The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are…
Point cloud compression is a key enabler for the emerging applications of immersive visual communication, autonomous driving and smart cities, etc. In this paper, we propose a hybrid point cloud attribute compression scheme built on an…
Learning a powerful representation from point clouds is a fundamental and challenging problem in the field of computer vision. Different from images where RGB pixels are stored in the regular grid, for point clouds, the underlying semantic…
In recent years, several point cloud geometry compression methods that utilize advanced deep learning techniques have been proposed, but there are limited works on attribute compression, especially lossless compression. In this work, we…