3d Rendering

2 posts

google2 min readCurated summary

It's all about the angle: Your photos, re-composed

Google’s new Auto frame feature in Google Photos re-composes photos by changing the apparent camera viewpoint after capture. It combines 3D scene reconstruction with generative AI to adjust framing, reduce wide-angle distortion, and generate background areas that were outside the original frame. The result is a more natural perspective while preserving the visible content and subjects’ identities. ## Why Traditional Editing Falls Short - Cropping and zooming cannot change the original camera perspective or parallax. - They also cannot reveal areas hidden outside the captured frame. - This is especially limiting for portraits, selfies, and “almost perfect” photos with poor framing or lens distortion. ## Two-Stage 3D-Aware Editing - **3D scene and camera estimation** - A machine-learning model creates a 3D point map from the 2D image using monocular depth estimation. - Each pixel is associated with an estimated 3D surface point. - The system estimates the original focal length and reconstructs human faces and bodies carefully to reduce identity-distorting artifacts. - Semantic analysis detects subjects’ face positions and 3D orientations to determine better camera parameters. - **Generative completion and retouching** - Classical 3D rendering produces an image from the modified camera position, orientation, and focal length. - Moving the virtual camera exposes “holes” where the original image contained no information. - A latent diffusion model fills these missing regions and corrects the rendered result. - Classifier guidance with regional scaling helps preserve original content while allowing generation in newly revealed areas. ## Automatic Framing and Distortion Correction - The system automatically selects camera parameters for improved portrait composition. - It can adjust both camera pose and intrinsic properties such as focal length. - For wide-angle selfies, it detects perspective distortion that enlarges features close to the lens. - By effectively moving the virtual camera backward and adjusting the optics, it produces more natural facial proportions. ## Availability in Google Photos - The technology is now integrated into the Auto frame feature. - It applies to eligible photos containing people. - Users receive the re-composed image as a second Auto frame candidate. - The enhancement requires only a single action and automatically changes the viewpoint while retaining the original scene. The feature demonstrates how combining geometric 3D reconstruction with controlled generative inpainting can perform edits that conventional cropping and retouching cannot. For portraits and selfies, Auto frame offers a practical way to improve composition and perspective after the moment has passed.

Read original(opens in new tab)
figma3 min readCurated summary

The Branding for Intercom’s AI Summit Looks Like an Alien Superbloom | Figma Blog

Intercom’s 2025 Pioneer AI summit branding uses an “alien superbloom” concept to express how rapidly AI is evolving. Its Creative Studio built a flexible system of surreal flowers, pollen-like particles, motion, and dot-matrix imagery that could work across digital campaigns, the website, event spaces, and merchandise. Figma served as the central workspace for exploration, collaboration, prototyping, feedback, and refinement. ## Building a Broad Creative Direction - Intercom Creative Studio began with expansive mood boards in Figma Design. - Teams combined motion clips, still images, vectors, logos, collages, and written concepts to explore multiple creative territories. - Motion designers, brand designers, and copywriters could experiment together in the same files. - Embedded video helped the team test logo treatments and messaging against motion references early in the process. - The selected direction evolved from the previous year’s “planted seeds” concept into an AI superbloom. ## Developing the Superbloom Visual Language - The central motif became surreal, alien-looking flowers blooming at unusual scales and speeds. - Pollen particles inspired a stippled aesthetic used in the logo, speaker portraits, and static imagery. - The visual system was designed to feel dynamic in motion while remaining restrained enough for print. - Intercom collaborated with Colors and the Kids to explore flower forms, animation styles, pollen density, and movement. - Figma Draw allowed designers to annotate video frames and specify changes to motion and flower shapes without switching applications. ## Presenting and Refining the Brand - Instead of conventional slide decks, the team presented concepts on long, scrollable Figma artboards. - Stakeholders could review work and leave comments directly on each board. - Separate pages organized successive feedback rounds, allowing explorations to develop into polished case studies. - Figma functioned both as a presentation tool and as an organizational system for the distributed 30-person creative team. ## Prototyping the Website - The Pioneer website was designed, prototyped, and quality-assured in Figma. - Designers and developers could review changes in one environment rather than moving between multiple platforms. - Live comments enabled immediate conversations during iteration, replacing slower back-and-forth through tools such as Slack. - The same brand principles could be tested across the web experience alongside event and campaign materials. The project demonstrates how a unified design workspace can help a distributed creative team move from broad visual exploration to a cohesive, motion-ready identity. For complex event branding, combining shared mood boards, in-context feedback, motion prototyping, and website testing can make the process faster and more connected.

Read original(opens in new tab)