Related papers: Class-Partitioned VQ-VAE and Latent Flow Matching …

The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly follow the progressive…

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing…

While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these…

In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts. Different to the existing methods which use separate networks for part generation and assembly, we propose a…

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…

Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research…

Vector Quantisation (VQ) is experiencing a comeback in machine learning, where it is increasingly used in representation learning. However, optimizing the codevectors in existing VQ-VAE is not entirely trivial. A problem is codebook…

Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the…

Indoor scene modification has emerged as a prominent area within computer vision, particularly for its applications in Augmented Reality (AR) and Virtual Reality (VR). Traditional methods often rely on pre-existing object databases and…

Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of…

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…

Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous…

This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the…

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Visual Question Answering on 3D Point Cloud (VQA-3D) is an emerging yet challenging field that aims at answering various types of textual questions given an entire point cloud scene. To tackle this problem, we propose the CLEVR3D, a…

We present a novel algorithm for point cloud segmentation. Our approach transforms unstructured point clouds into regular voxel grids, and further uses a kernel-based interpolated variational autoencoder (VAE) architecture to encode the…

We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion. Flow computed at the coarse level is upsampled and warped to a finer level, enabling the algorithm to accommodate for…

This paper tackles the problem of parts-aware point cloud generation. Unlike existing works which require the point cloud to be segmented into parts a priori, our parts-aware editing and generation are performed in an unsupervised manner.…

While recent work on text-conditional 3D object generation has shown promising results, the state-of-the-art methods typically require multiple GPU-hours to produce a single sample. This is in stark contrast to state-of-the-art generative…

Locating and retrieving objects from scene-level point clouds is a challenging problem with broad applications in robotics and augmented reality. This task is commonly formulated as open-vocabulary 3D instance segmentation. Although recent…