Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering

from a small set of neighboring images.For fusion, we use a neural blending weight from a shallow MLP.We optimize the local Gaussian density mixtures using both a reconstruction loss and a consistency loss.The consistency loss, based on per-ray KL-divergence, encourages more accurate geometry reconstruction.In scenes with complex reflections captured in our LGDM dataset, the experimental results show that our method outperforms stateof-the-art novel view synthesis methods by 12.2%-37.1% in PSNR, due to its ability to maintain sharper view-dependent appearances.Project webpage: https://xchaowu.github.io/papers/lgdm/index.html

Authors

Institutions

Publication Details

Published
2024-12-03
DOI
https://doi.org/10.1145/3680528.3687659
Citations
1
Primary Topic
Advanced Vision and Imaging
Type
article
Field-Weighted Citation Impact
0.25

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering

Qixing Huang, James Tompkin, Chi Wang, Jiamin Xu et al.
1 citations
Advanced Vision and Imaging
0.25
article

Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering

Qixing Huang, James Tompkin, Chi Wang, Jiamin Xu, Yifan Peng, Weiwei Xu, X Wu
article en
1 citations

Abstract

from a small set of neighboring images.For fusion, we use a neural blending weight from a shallow MLP.We optimize the local Gaussian density mixtures using both a reconstruction loss and a consistency loss.The consistency loss, based on per-ray KL-divergence, encourages more accurate geometry reconstruction.In scenes with complex reflections captured in our LGDM dataset, the experimental results show that our method outperforms stateof-the-art novel view synthesis methods by 12.2%-37.1% in PSNR, due to its ability to maintain sharper view-dependent appearances.Project webpage: https://xchaowu.github.io/papers/lgdm/index.html

Brown University (US), Hangzhou Dianzi University (CN), Zhejiang University (CN), The University of Texas at Austin (US), University of Hong Kong (HK)
National Science Foundation, Ant Group, National Natural Science Foundation of China, Zhejiang University, Natural Science Foundation of Zhejiang Province
Sustainable cities and communities
Openalex Percentile: Top 44%
Advanced Vision and Imaging
0.25
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering — Qixing Huang, James Tompkin, et al. · (2024) | TGRS Research Map | TGRS