SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.12408 · CVPR · 2023

Balanced Spherical Grid for Egocentric View Synthesis

Changwoon Choi, Young Kim, Sang Kim

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Optimize 𝒢 ! 𝒢 % tiny 𝑓 ()* 𝜎(𝐱) 𝑐(𝐱, 𝐝) Render Figure 1. We propose a practical solution to reconstruct large-scale scenes from a short egocentric video. (a) Our scalable capturing setup observes the holistic environment by casually swiping a selfie stick with an omnidirectional camera attached. (b) Then we optimize our balanced spherical feature grids which are tailored for the outward-looking setup. (c) EgoNeRF can quickly train and render high-quality images at nearby positions. Project

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.12408")
get_code_for_paper("2303.12408")
have("2303.12408")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.12408.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.12408.svg)](https://syntology.ai/paper/2303.12408)

Connect an agent — have() is free.