| --- |
| license: apache-2.0 |
| tags: |
| - gaussian-splatting |
| - 3d-reconstruction |
| - novel-view-synthesis |
| - feed-forward |
| datasets: |
| - DL3DV/DL3DV-10K |
| --- |
| |
| # TokenGS-Loop |
|
|
| Feed-forward 3D Gaussian splatting from 4 posed views at 256×256, built on [LocusGS](https://github.com/leo-frank/LocusGS) / [TokenGS](https://github.com/nv-tlabs/TokenGS). |
| The stack of 12 independent LocusGS decoder layers is replaced by **one decoder layer unrolled 12 times with shared weights**. Three additions make this work: |
|
|
| - round-conditioned FiLM gates; |
| - render-error feedback from the input views; |
| - stop-gradient between the error-free first round and the refinement rounds. |
|
|
| | file | branch | tokens | PSNR | LPIPS | SSIM | |
| |---|---|---|---|---|---| |
| | `errenc-sg/model.safetensors` (epoch 26) | `errenc-sg` | 1024 | 23.706 | 0.3043 | 0.7586 | |
| | `split-clone/model.safetensors` (epoch 17) | `split-clone`: error-guided token splitting, opacity-corrected children | 364 → 1024 | 23.301 | 0.3401 | 0.7387 | |
| | LocusGS stage 1, released `base` weights (reference, same evaluation) | – | 1024 | 24.154 | 0.2766 | 0.7805 | |
|
|
| All rows use the official DL3DV benchmark: 140 scenes, 4 input views, 256×256, all 50 target frames. |
|
|
| Code: GitHub `Yusin2Chen/TokenGS-Loop`, branches `errenc-sg` and `split-clone`. Each branch README describes the method, evaluation and training commands. The checkpoints contain the weights of decoder blocks 1–11 inherited from initialization; only block 0 is executed. |
|
|
| License: Apache-2.0 (derived from LocusGS / TokenGS). |
|
|
