Part-Controllable 3D Generation Flow Model Diagram
Overview
A left-to-right pipeline for locally controllable 3D generation: spatial primitives, text prompts and reference images go through ℰ, ℰ_clip and ℰ_dino encoders; a Structure Flow Model splits the schedule into Skip / Conditioned Flow / Flow segments between τ_low and τ_high; a structure decoder D_s, part segmentation and condition routing feed a Texture Flow Model (Flow Transformer + Self-Similarity Guidance). It is an editable PowerPoint diagram adapted from the original paper figure under CC BY 4.0.
What the diagram shows
Every box, arrow, label and math term is a native shape you can recolor, resize and relabel for your own slides, posters or papers.
File format
The download contains .pptx (1 slide, 13.32 × 4.08 in; opens in PowerPoint, Keynote, WPS and LibreOffice Impress; Google Slides works too, but complex freeforms may shift slightly), .svg and .drawio. Includes preview.png (full resolution) and a 1200 px web preview.
Shapes and editing
The file has 100 native editable shapes: 31 auto-shapes, 36 text boxes, 17 freeforms, 16 lines/connectors. 11 embedded images (see below). You can edit all labels and math (ℰ_clip, ℰ_dino, τ_low, τ_high, D_s, 𝒯), encoder trapezoids, the three-segment flow bar, token color stacks, dotted conditioning arrows, the switch symbol and the legend boxes.
Embedded images and fonts
11 items are embedded images: the 3D airplane renders, point clouds and the reference-image stack. Text uses Times New Roman, which is preinstalled on Windows and macOS (LibreOffice uses the metric-compatible Liberation Serif). A few calligraphic math letters (such as 𝒩, ℰ, 𝒮) use Cambria Math, which ships with Microsoft Office; other apps substitute a math font. Sub- and superscripts are real formatted text runs, not equation objects. The SVG keeps text as text; the draw.io file is a shape-by-shape conversion and may need small nudges. This is a faithful redraw for reuse, not the authors' original source file.
Source & license Adapted from Figure 2 of SpaceFlow: Locally Controllable 3D Generation by Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov, Felicia Scharitzer, Marc Pollefeys, Ata Celen, Sayan Deb Sarkar, Elisabetta Fedele (arXiv:2610.12399, https://arxiv.org/abs/2610.12399; code: https://github.com/SpaceFlow3D/spaceflow). Licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Redrawn as editable shapes; changes made by 叫我Alonzo就好了/alonzolab. Not endorsed by the original authors. Attribution to the original paper is required when you publish or share the figure; the exact credit line is in LICENSE-ATTRIBUTION.txt inside each download.