VAST-AI-Research/Mira-Scene
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction
About the project
Generative reconstruction of an editable 3D scene from a single image: segmentation, depth estimation, voxel prediction, and object mesh assembly.
Useful for
- Reconstruct an editable 3D scene from a single image via the stage-wise inference pipeline
- Train the model in two stages: pretrain with pretrain_l1.yaml, then finetune
- Reproduce reported reconstruction metrics (CD, FS, 3D-IoU) against the benchmark table
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 5 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 5 days old and already has 78 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #197.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 78
- Today
- 0 · ≈ 5 by evening
- Forks
- 0
- Issues and pull requests
- 1
- Watchers
- 1
- Language
- Python
- Created
- September 20, 2026
- Last push
- September 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 25, 2026Top new repositories this week: #196
More in this category
-
6.6
BridgeDruidCompress/Moon-FruityLoops26-FileParser
Binary parser for FL Studio project files (.flp): reads header, chunks and events into patterns, channels and automation. Provides programmatic access to FL Studio project contents.
-
6.5
yukitorido/short-video-generator-AI
Open-source Python pipeline that turns long YouTube videos into vertical short clips: faster-whisper transcription, LLM highlight detection and auto-cropping to 9:16.
-
6.2
JohnHeibel/PDoomVideo
Source code for a music video generated entirely by Claude Opus, with scenes, lyrics and transitions built in p5.js and rendered to MP4 via headless Chrome and ffmpeg.
-
5.9
bridge-mind/bridgeclip
Open-source desktop app that turns long videos into short captioned clips: it finds the best moments, crops to 9:16 or 16:9, and burns in word-by-word captions. Runs locally, calling OpenRouter with your own keys.
-
5.8
harry7557558/spirula-studio
A self-contained C++ binary for training 3D Gaussian Splatting models: turns photos and video into splats and textured meshes, running on NVIDIA, AMD, Intel and Apple GPUs via Vulkan or CUDA without Python or COLMAP.
-
5.8
JohnHeibel/ClaudeAnimationBase
A starter kit for animating the hand-painted character Clawd in p5.js and p5.brush with Claude: code, 31 emotions, model sheets and the ANIMATION_GUIDE.md for the model.