paper-with-me

Papers

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

2023-03-10 · CVPR 2023 1 · Mingfang Zhang, Jinglu Wang, Xiao Li, Yifei HUANG, Yoichi Sato, Yan Lu

The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view synthesis from sparse inputs. Yet, its fixed structure limits the performance, especially for surfaces imaged at oblique angles. We introduce the Structural MPI (S-MPI), where the plane structure approximates 3D scenes concisely. Conveying RGBA contexts with geometrically-faithful structures, the S-MPI directly bridges view synthesis and 3D reconstruction. It can not only overcome the critical limitations of MPI, i.e., discretization artifacts from sloped surfaces and abuse of redundant layers, and can also acquire planar 3D reconstruction. Despite the intuition and demand of applying S-MPI, great challenges are introduced, e.g., high-fidelity approximation for both RGBA layers and plane poses, multi-view consistency, non-planar regions modeling, and efficient rendering with intersected planes. Accordingly, we propose a transformer-based network based on a segmentation model. It predicts compact and expressive S-MPI layers with their corresponding masks, poses, and RGBA contexts. Non-planar regions are inclusively handled as a special case in our unified framework. Multi-view consistency is ensured by sharing global proxy embeddings, which encode plane-level features covering the complete 3D scenes with aligned coordinates. Intensive experiments show that our method outperforms both previous state-of-the-art MPI-based view synthesis methods and planar reconstruction methods.

📄 PDF Abstract BibTeX arXiv:2303.05937

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Single-View View Synthesis with Multiplane Images

2020-04-23 · CVPR 2020 6 · Richard Tucker, Noah Snavely

A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to…

Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations

2023-03-31 · CVPR 2023 1 · Thomas Tanay, Aleš Leonardis, Matteo Maggioni

While current multi-frame restoration methods combine information from multiple input images using 2D alignment techniques, recent advances in novel view synthesis are paving the way for a new paradigm relying on volumet…

DenoisingNovel View Synthesis

SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images

2023-12-18 · Guo Pu, Peng-Shuai Wang, Zhouhui Lian

Single-image novel view synthesis is a challenging and ongoing problem that aims to generate an infinite number of consistent views from a single input image. Although significant efforts have been made to advance the qu…

Novel View Synthesis

SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image

2023-09-12 · ICCV 2023 1 · Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang 외

Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as inpu…

Novel View Synthesis

Remote Sensing Novel View Synthesis with Implicit Multiplane Representations

2022-05-18 · Yongchang Wu, Zhengxia Zou, Zhenwei Shi

Novel view synthesis of remote sensing scenes is of great significance for scene visualization, human-computer interaction, and various downstream applications. Despite the recent advances in computer graphics and photog…

Novel View Synthesis