Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Preview of 17438233423567390063739333297395-jpeg

Fail How To (Not) Wieden+Kennedy Amsterdam Or: Why There Is No Audience For What We Make And Why That Truth Will Set Us Free

The text critiques common marketing assumptions, emphasizing that most consumers lack strong relationships with brands and suggesting that marketing efforts should focus on engaging a broader audience rather than nurturing fan loyalty.

Link

CamViG Camera Aware Image-to-Video Generation with Multimodal Transformers We extend multimodal transformers to include 3D camera motion as a conditioning signal for the task of video generation. Generative video models are becoming increasingly powerful, thus focusing... See more

x.com

a 3d scanning of me in fort greene park two summers ago. multiple virtual cameras spatially frame the scan from different angles, fragmenting presence through distributed viewpoints. #touchdesigner #touchdesignerlearning #touchdesignercommunity #newmediaart #creativecoding #generativeart #interfacedesign #polycam... See more

the.poet.engineer instagram.com

Thumbnail of www-x-com-tom-doerr-status-1966466317403267360-40fb6dab923d4df6

Unified library for multi-object tracking algorithms with modular design and easy integration https://t.co/4aVMxnI5nM

Tom Dörr

x.com

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos Contributions: • An incremental joint optimization approach for simultaneous camera pose and 3DGS reconstruction, reducing local minima and ensuring global consistency. • A robust pose estimation module... See more

MrNeRF x.com

Thumbnail of www-x-com-zhenjun-zhao-status-1760875413734064481-4be00e2f44134384

Cameras as Rays: Pose Estimation via Ray Diffusion Jason Y. Zhang, Amy Lin, Moneish Kumar, Tzu-Hsuan Yang, @RamananDeva, @shubhtuls tl;dr: predict a separate ray passing through each patch in each input image->least-square->camera extrinsics&intrinsics https://t.... See more

Zhenjun Zhao

x.com

Happyend: A Japanese teen sci-fi set in a dystopian, AI-driven future

webcam effects with HTML canvas 🎥 note to self:: finish old demos https://t.co/5CXK9YYEka

jhey ʕ•ᴥ•ʔ x.com