相关论文: Large Point-to-Gaussian Model for Image-to-3D Gene…

Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e.g., LiDAR in autonomous or assisted driving). In many cases, such volume of data is transmitted, thus…

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or…

Traditional 3D content representations include dense point clouds that consume large amounts of data and hence network bandwidth, while newer representations such as neural radiance fields suffer from poor frame rates due to their…

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep…

By enabling capturing of 3D point clouds that reflect the geometry of the immediate environment, LiDAR has emerged as a primary sensor for autonomous systems. If a LiDAR scan is too sparse, occluded by obstacles, or too small in range,…

This work introduces a new task of instance-incremental scene graph generation: Given a scene of the point cloud, representing it as a graph and automatically increasing novel instances. A graph denoting the object layout of the scene is…

Traditional explicit 3D representations, such as point clouds and meshes, demand significant storage to capture fine geometric details and require complex indexing systems for surface lookups, making functional representations an efficient,…

We present a learning-based approach to reconstruct buildings as 3D polygonal meshes from airborne LiDAR point clouds. What makes 3D building reconstruction from airborne LiDAR hard is the large diversity of building designs and especially…

In this paper, we propose an effective point cloud generation method, which can generate multi-resolution point clouds of the same shape from a latent vector. Specifically, we develop a novel progressive deconvolution network with the…

We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in…

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

Articulated object generation has seen increasing advancements, yet existing models often lack the ability to be conditioned on text prompts. To address the significant gap between textual descriptions and 3D articulated object…

Point cloud is a collection of 3D coordinates that are discrete geometric samples of an object's 2D surfaces. Using a low-cost 3D scanner to acquire data means that point clouds are often in lower resolution than desired for rendering on…

Accurate 3D reconstruction of dynamic surgical scenes from endoscopic video is essential for robotic-assisted surgery. While recent 3D Gaussian Splatting methods have shown promise in achieving high-quality reconstructions with fast…

We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian…

Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions,…

Representation and generative learning, as reconstruction-based methods, have demonstrated their potential for mutual reinforcement across various domains. In the field of point cloud processing, although existing studies have adopted…

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical…

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is a unified,…