microsoft/renderformer

A Cornell box turned into a cover page: a red, green and blue cube logo, a two-line ruled title, a black gallery of rendered scenes, then a nested contents list that maps the whole manual.

github.com/microsoft/renderformermicrosoft/renderformer
Screenshot of https://github.com/microsoft/renderformer, © the authors. Shown for reference. Request removal
Venue
SIGGRAPH 2025
Year
2025
First author
Chong Zeng
Field
neural rendering
Template
320px square logo, centred h1 paper title, bold author links joined by middots, centred h2 venue, full-width gallery with plain caption, bold text-link row separated by pipes
Theme
Light

Checked against the rendered page. Three table-of-contents anchors in the README (#usage-1, #inference-with--renderformerrenderingpipeline-, #bring-your-own-scene-) do not match GitHub's generated heading ids, so those links do not jump; recorded in Section Outline.

Why it is here

A model first screen: a square logo, centered title, author line, venue line, a sharp captioned teaser grid, a single row of text links, then a full nested table of contents that maps the whole manual before installation starts.

Overview

Header Block

Badge Colors

Section Outline

Guidelines

More like this