One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation

A product launch at midnight: a tiled video wall sinking into indigo, an ice-cyan gradient headline floating over it, and blueprint-gridded cards waiting below the fold.

gzwsama.github.io/OnePoseviaGen.github.ioOne View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
Screenshot of https://gzwsama.github.io/OnePoseviaGen.github.io/, © the authors. Shown for reference. Request removal
Venue
CoRL 2025 (Oral)
Year
2025
First author
Zheng Geng
Field
6D pose estimation
Template
custom Tailwind CDN page (three.js, GSAP)
Theme
Dark

Checked against the rendered page. Only the hero is visible in the screenshots (h-screen stretches in the tall capture); below-the-fold sections documented from DOM probes. Page shows no venue or affiliations.

Why it is here

Dark gradient overlay on a tiled video wall with a cyan gradient title and a gradient demo button. A bold startup-like hero not found elsewhere in the picks, though only the hero is visible in the capture.

Overview

Color Palette

Typography

Inter 400
One View, Many Worlds: Single-Image to 3D Object Meets Generative Doma Abstract · Method · Results · BibTeX — 0123456789
Inter 600
One View, Many Worlds: Single-Image to 3D Object Meets Generative Doma Abstract · Method · Results · BibTeX — 0123456789
Inter 700
One View, Many Worlds: Single-Image to 3D Object Meets Generative Doma Abstract · Method · Results · BibTeX — 0123456789

Spacing & Shape

Page Modules

Guidelines

More like this