Search papers, labs, and topics across Lattice.
5
0
7
3
LLM/VLM agents significantly outperform non-agentic methods in preserving unedited parts during iterative 3D asset modification, but current agentic edits are prohibitively slow.
KaiNinja, a part-level extension of TRELLIS.2 built on a dual-volume form of its O-Voxel representation, is the first 3D generative model trained on agent-authored part data and finds that whole-object fidelity improves over the same backbone fine-tuned on the same dataset.
Monolithic 3D scenes with hundreds of heavily occluded objects can be cleanly parsed into individual editable meshes without ever training on multi-object data.
Training generative inverse renderers on AAA game footage closes the realism gap, enabling superior generalization and controllable generation compared to models trained on existing synthetic datasets.
