Stability AI just launched Arbor, a 600MB control system that brings precise spatial constraints to 3D asset generation. Instead of rolling the dice with text prompts, creators can now use rough guide meshes to dictate exact volumes, empty clearances, and contact surfaces without retraining base models. It is fully open-sourced to work alongside Trellis.
Researchers just unveiled GenRecon, a technique that reconstructs large-scale indoor 3D scenes from sparse RGB photos. By tiling overlapping chunks and lifting Trellis.2 generative priors to the scene level, it outputs editable PBR meshes and outperforms cutting-edge baselines by 16%. It brings casual smartphone snaps much closer to replacing expensive professional scanners for VR and game design.
SegviGen just open-sourced a 3D part segmentation framework built on TRELLIS.2 that splits meshes into individual components via single clicks or 2D guide images. It outperforms previous SOTA models by 40% in interactive segmentation while requiring far less supervision, though local inference demands at least 24GB of VRAM.
Microsoft researchers just released TRELLIS.2-4B, an open-source 4-billion-parameter model that converts a single image into high-fidelity 3D assets with full PBR materials. Built on a novel sparse voxel structure called O-Voxel, it can produce 512³ resolution assets in about 3 seconds on an H100 GPU, though it demands an NVIDIA GPU with at least 24GB of memory.
