SceneGen Generates 3D Scenes from a Single Image in One Feedforward Pass
tom_doerr · x · 2026-08-10
SceneGen, accepted to 3DV 2026, introduces a novel architecture capable of generating complete 3D scenes from a single image in just one feedforward pass.
The project's training code, inference scripts, data processing toolkits, and pretrained models have been fully open-sourced on GitHub. Developers can deploy and reproduce the results locally with supported hardware (e.g., NVIDIA GPUs).
More from Multimodal
- Seeking a Stable Workflow for Reference-to-Video Character Swap — Wonderful-Tough7215 · 2026-08-10
- Testing Seedance 2.5: Generating 30s Videos with Multiple References — CurieuxExplorer · 2026-08-10
- AI 'Invisible Mode' Showcases Mind-Bending Video Generation — ThAIandTed · 2026-08-10
- Google XR Open-Sources GNM Parametric Human Models, Community Builds Interactive Visualizer — leland_mcinnes · 2026-08-10
- Blur2Vid: Generating Videos from Motion-Blurred Images — cindy_x_wu · 2026-08-10
- Creating Long-form Virtual Perfume Ads Using Seedance 2.5 — JeffSynthesized · 2026-08-10