Back to search

Cal Poly

DeepPanoRF: Deep Prior for Neural 3D Reconstruction From Sparse Panoramas

Abstract

dc:description.abstract

Advances in neural field representations have led to a significant improvement in view synthesis quality. However, many current novel view synthesis methods rely on a dense set of input views, which can be impractical and inefficient in real-world applications. We propose DeepPanoRF, a novel method for 360◦ scene reconstruction from a sparse set of input equirectangular panoramas. Built upon K-Planes, a radiance field representation that encodes explicit features on orthogonal feature planes, our method does not directly learn feature grids. Instead, we parameterize the feature grids to enable sparse view reconstruction without pretraining or additional regularization. We implement a custom U-Net architecture to take advantage of the encoder-decoder network and the skip connections. We evaluate our method’s effectiveness on the Habitat-Matterport 3D (HM3D) dataset, which consists of diverse, high-quality indoor environments. Our results demonstrate that DeepPanoRF outperforms K-Planes in both reconstruction quality and structural coherence when dealing with sparse input views.

Degree

thesis:*
Name thesis:degree_name
MS in Computer Science
Discipline thesis:degree_discipline
Computer Science

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Du, Edward
Contributors dc:contributor
  • Jonathan Ventura
  • Computer Science
  • College of Engineering

Subjects

dc:subject × 7

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.calpoly.edu/theses/2995

Chain of custody

source
Harvested from
Cal Poly
Base URL
digitalcommons.calpoly.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Du, Edward. DeepPanoRF: Deep Prior for Neural 3D Reconstruction From Sparse Panoramas. https://digitalcommons.calpoly.edu/theses/2995