paper-with-me

Papers

Multiresolution Deep Implicit Functions for 3D Shape Representation

2021-09-12 · ICCV 2021 10 · Zhang Chen, yinda zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Haene, Ruofei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang

We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape completion quality under decoder-only latent optimization. To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion. Experiments demonstrate its superior performance against prior art in various 3D reconstruction tasks.

📄 PDF Abstract BibTeX arXiv:2109.05591

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction3D Shape RepresentationDecoder

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Local Deep Implicit Functions for 3D Shape

2019-12-12 · CVPR 2020 6 · Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna 외

The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape cat…

3D Shape RepresentationSurface Reconstruction

LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions

2024-02-11 · Atharva Pandey, Vishal Yadav, Rajendra Nagar, Santanu Chaudhury

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have…

Surface Reconstruction

Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions

2025-11-21 · Neel Sortur, Justin Goodwin, Purvik Patel, Luis Enrique Martinez 외 arxiv

Determining the shape of 3D objects from high-frequency radar signals is analytically complex but critical for commercial and aerospace applications. Previous deep learning methods have been applied to radar modeling; ho…

3D Shape Reconstruction3D Reconstruction

ANISE: Assembly-based Neural Implicit Surface rEconstruction

2022-05-27 · Dmitry Petrov, Matheus Gadelha, Radomir Mech, Evangelos Kalogerakis

We present ANISE, a method that reconstructs a 3D~shape from partial observations (images or sparse point clouds) using a part-aware neural implicit shape representation. The shape is formulated as an assembly of neural …

Point cloud reconstructionRetrievalSurface Reconstruction

Learning Shape Templates with Structured Implicit Functions

2019-04-12 · ICCV 2019 10 · Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna 외

Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of …

Semantic Segmentation