Linus Ekenstam launches Video Volume 3D tool

// 1h agoPRODUCT LAUNCH

Linus Ekenstam launches Video Volume 3D tool

Video Volume is a browser-based micro-tool developed by Linus Ekenstam using Astra that enables users to upload MP4 or MOV video files and explore them as 3.5D spatio-temporal volumes. Inspired by slit-scan techniques, the tool maps video frames across spatial and temporal dimensions with linked 2D and 3D perspectives, processing all frames locally on-device.

// ANALYSIS

Turning linear video into an interactive 3D time volume transforms ephemeral motion into an inspectable sculpture, highlighting how AI-assisted workflows empower solo creators to rapidly turn conceptual visual experiments into working web tools.

–Spatio-Temporal Slicing: Maps the timeline directly to a spatial dimension (X, Y, T), allowing users to orbit, zoom, and inspect motion trajectories across time.
–Local Client-Side Execution: Video decoding and volume generation run completely on the local device, ensuring user privacy and low latency.
–Rapid AI-Assisted Prototyping: Demonstrates the ease with which makers can ship functional, well-designed micro-apps in a single evening using modern AI coding tools.
–Creative and Diagnostic Potential: Beyond artistic exploration, volumetric video slicing serves practical use cases in motion analysis and generative video artifact inspection.

// TAGS

video3dcomputer-visionvisualizationcreative-techbrowser-toolsmotion-design

DISCOVERED

1h ago

2026-09-21

PUBLISHED

2h ago

2026-09-21

RELEVANCE

6/ 10

AUTHOR

LinusEkenstam

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL1h ago

Mev drops 0.4B candidate matching decision model

Mev is a lightweight 0.4-billion-parameter AI decision model designed specifically for recruitment and talent acquisition workflows. Built on the non-autoregressive paradigm popularized by models like Jev, Mev evaluates candidates against job descriptions in a single forward pass without generating text.

MODEL2h ago

Yandex open-sources Alice AI Foundation LLM

Yandex has released Alice AI Foundation LLM (AliceAI-Foundation-80B-A3B-Base), an 80-billion-parameter Mixture-of-Experts base model with 3 billion active parameters published under an Apache 2.0 license on Hugging Face. Trained from scratch for reasoning and agentic workflows, the model demonstrates strong math and code synthesis while introducing two new Russian-language factual benchmarks, WikiWebFacts and HardMultiQA.

MODEL2h ago

StepFun drops Step 5 Preview 600B MoE

StepFun introduced Step 5 Preview, a 600-billion-parameter Mixture-of-Experts (MoE) model that routes through 27 billion active parameters per token. Equipped with a 1-million-token context window and native multimodal vision support, the model is targeted specifically at high-demand domains including software development and financial analytics. StepFun claims that Step 5 Preview matches the frontier performance benchmarks of GLM 5.3 and Kimi K3 while cutting per-task inference costs by roughly 65%, with open model weights scheduled for public release on October 15.

Linus Ekenstam launches Video Volume 3D tool