ML For 3D Data

Most researcher transform Point Cloud data to regular 3D voxle grids or collections of images to perform weight sharing and kernerl optimizations due

🚀 Motivations PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained p

State-of-the-art deep neural networks are designed specifically to handle the irregularity of point clouds, directly manipulating raw point cloud data

🚀 Motivations🔑 Key Contribution🤔 Problem Statement⭐ MethodsThis paper suggests each 3 version of PointOutNet.✅ Conclusion

Recents attempts to encode 3D geometry for use in deep learning include view-based projections, volumetric grids and graphs.➡️ This paper focuses on t

Classical and compact surface representations such as triangle or quad meshes pose problems in training beacause possible needs to deal with an unknow

In generative modeling of 3D shapes, the shapes produced by SOTA methods still fall far short in terms of visual quality.This is reflected by a combin

Unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-reso

Existing categories for 3D representations (voxel, polygon meshes, point clouds) all suffer from different drawbacks and present differenet disadvanta

Recent 3D deep learning methods infer general shapes from very few images, even a single input. However, the resulting resolutions and accuracy are li

While many single-view 3D reconstruction methods that learn a shape embedding from a 2D image are able to capture the global shape properties, they ha

Current network architectures for such implicit neural representations are 1) incapable of modeling signals with fine dietail, 2) fail to represent a

Motivations standard MLPs are poorly suited for low-dimensional coordinate-based vision and graphic tasks.MLPs have difficulty learning high frequency

Lack of 3D understating of generative neural networks by introducing a persistent 3D feature embedding for view synthesis.While Techniques based on ex

🔑 Key Contributions This paper presents an end-to-end pipeline for rendering images from novel views with only image supervision that leverages an in

This paper presents a method forsynthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene functionusing a spa

🚀 Motivations3D semantic attributes (such as segmentation masks, geometric features, keypoints, and materials) can be encoded as per-point probe func

Co-segmentation is intrinsically contextual: how a shape is segmented can vary depending on the set it is in.➡️ Paper's network features an adaptive l

🚀 Motivations🛩️ Approach🔑 Key Contributions⭐ Methods👨🏻‍🔬 Experimental Results

Current 3D object detection methods are heavily influenced by 2D detectors.In order to leverage architecture in 2D detectors, they often conver 3D poi

🚀 Motivations 1️⃣ Few recent works have SOTA performance with just point clouds input (e.g. VOTENET) VOTENET showed remarkable improvement for indoor object recognition compared with previous works ...

🚀 Motivations CNN has boosted the performance of 2D segmentation. However, given unordered and unstructured 3D point clouds, 2D methods cannot be dir

🚀 Motivations Polygonal meshes are ubiquious in the digital 3D domain, yet a minor role in deep learning revolution. Leading methods for learning ge

🚀 Motivations Any solid object can be decomposed into a collection of convex polytopes (in short, convexes). This decomposition is fundamental in co

Methods based on SDF struggle to reconstruct non-convex shapes.One remedy is to incorporate a CSG(constructive solid geometry) frameworkthat represent

Generating an interpretable and compatrepresentation of 3D shapes from point cloudis an important and challenging problem.✅ This paper presents CSG-

Author: Juil Koo, Seungwoo Yoo, Minh Hieu Nguyen, Minhyuk SungRecent research on 3D diffusion models has focuesd on improving their generation capabil