rsasaki0109 (@rsasaki0109)
2025-12-31 | โค๏ธ 279 | ๐ 32
3D-RE-GEN 3D Reconstruction of Indoor Scenes with a Generative Framework https://github.com/cgtuebingen/3D-RE-GEN We propose single-image 3D scene reconstruction for producing complete, editable scenes from a single photograph. Our method reconstructs individual objects and the surrounding background as textured 3D assets, enabling coherent scene assembly from minimal input. We combine instance segmentation, context-aware generative inpainting, 2D-to-3D asset creation, and constrained optimization to recover physically plausible geometry, materials, and lighting. The resulting scenes preserve correct spatial relationships, lighting consistency, and material fidelity, making them suitable for production-ready workflows.
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
๐ Related
- objsplat-geometry-aware-gaussian-surfels-for-active-object
- gen3r-3d-scene-generation-meets-feed-forward-reconstruction
- gaussianfluent-explicit-gaussian-simulation-for-dynamic
- actionmesh
- 360anything-geometry-free-lifting-of-images-and-videos-to