sparse_structure_decoder missing from TRELLIS.2 — references incompatible original TRELLIS checkpoint

The pipeline.json in microsoft/TRELLIS.2-4B references:

"sparse_structure_decoder": "microsoft/TRELLIS-image-large/ckpts/ss_dec_conv3d_16l8_fp16"

This checkpoint is from the original TRELLIS repo and is not compatible with TRELLIS.2's flow model. When used, the decoder produces all-negative values (range approximately -200 to -70) regardless of input, resulting in zero valid voxels and broken 3D reconstruction.

Expected: TRELLIS.2 should include its own sparse_structure_decoder checkpoint trained to match its flow model output distribution.

Workaround attempted: Using a percentile threshold (top 50%) instead of > 0 produces voxels but they are geometrically incorrect (cube-shaped noise).

Environment: Google Colab A100, PyTorch 2.10, CUDA 12.8

Please either include the correct TRELLIS.2 sparse structure decoder in the model release, or update pipeline.json to point to a compatible checkpoint.

Start by inspecting pipeline.json and the referenced sparse_structure_decoder checkpoint path. Compare that checkpoint with TRELLIS.2's flow-model output expectations, then determine whether a compatible checkpoint exists or must be released. Done means pipeline.json uses a compatible decoder and 3D reconstruction produces valid, geometrically correct voxels.