ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914589913907200 |
|---|---|
| author | Li, Yuke Liu, Weihang Zhang, Cheng Zhang, Yuefeng Cui, Jiadi Wang, Zixuan Ding, Junran Wu, Haoyu Shi, Yujiao Yu, Jingyi Lou, Xin |
| author_facet | Li, Yuke Liu, Weihang Zhang, Cheng Zhang, Yuefeng Cui, Jiadi Wang, Zixuan Ding, Junran Wu, Haoyu Shi, Yujiao Yu, Jingyi Lou, Xin |
| contents | Feed-forward 3D Gaussian Splatting models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations. A practical compromise is predict-then-refine,where post-prediction optimization compensates for the limited capacity of the feed-forward network. However,standard feed-forward 3DGS is trained solely for zero-step rendering error,ignoring whether its output constitutes a good initialization for the downstream optimizer. We present ForeSplat,an optimization-aware training framework that equips feed-forward 3DGS models to produce initializations explicitly designed for rapid,effective refinement. By offloading part of the scene-modeling burden to the optimizer,ForeSplat substantially reduces the capacity pressure on the feed-forward model,making high-quality reconstruction feasible even with compact networks. At its core is MetaGrad,a lightweight multi-anchor meta-gradient training rule that bypasses costly higher-order differentiation through the 3DGS optimizer. MetaGrad unrolls a short inner-loop refinement trajectory,samples anchor states,and back-propagates aggregated first-order gradients to the prediction head as a surrogate optimization-aware signal. This fine-tuning adds no inference cost and enables high-quality reconstruction within seconds after a few refinement steps. We instantiate ForeSplat on diverse backbones,including AnySplat,Pi3X,and a distilled variant tailored for edge deployment. Across all tested architectures,a ForeSplat-trained initialization converges in fewer refinement steps and reaches a higher peak reconstruction quality than its vanilla counterpart,even fully converged. The framework consistently bridges the gap between amortized prediction and per-scene optimization,establishing a practical path toward lightweight,high-fidelity 3D reconstruction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22020 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting Li, Yuke Liu, Weihang Zhang, Cheng Zhang, Yuefeng Cui, Jiadi Wang, Zixuan Ding, Junran Wu, Haoyu Shi, Yujiao Yu, Jingyi Lou, Xin Computer Vision and Pattern Recognition Feed-forward 3D Gaussian Splatting models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations. A practical compromise is predict-then-refine,where post-prediction optimization compensates for the limited capacity of the feed-forward network. However,standard feed-forward 3DGS is trained solely for zero-step rendering error,ignoring whether its output constitutes a good initialization for the downstream optimizer. We present ForeSplat,an optimization-aware training framework that equips feed-forward 3DGS models to produce initializations explicitly designed for rapid,effective refinement. By offloading part of the scene-modeling burden to the optimizer,ForeSplat substantially reduces the capacity pressure on the feed-forward model,making high-quality reconstruction feasible even with compact networks. At its core is MetaGrad,a lightweight multi-anchor meta-gradient training rule that bypasses costly higher-order differentiation through the 3DGS optimizer. MetaGrad unrolls a short inner-loop refinement trajectory,samples anchor states,and back-propagates aggregated first-order gradients to the prediction head as a surrogate optimization-aware signal. This fine-tuning adds no inference cost and enables high-quality reconstruction within seconds after a few refinement steps. We instantiate ForeSplat on diverse backbones,including AnySplat,Pi3X,and a distilled variant tailored for edge deployment. Across all tested architectures,a ForeSplat-trained initialization converges in fewer refinement steps and reaches a higher peak reconstruction quality than its vanilla counterpart,even fully converged. The framework consistently bridges the gap between amortized prediction and per-scene optimization,establishing a practical path toward lightweight,high-fidelity 3D reconstruction. |
| title | ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.22020 |