StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2608.01659v2
• Date: Wed, 05 Aug 2026 02:38:41 GMT
• Title: StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting
• Abstract summary: StreamSplat is a feed-forward 3DGS framework that incrementally maintains a persistent geometry-grounded scene state.<n>Experiments show that StreamSplat remains competitive with state-of-the-art feed-forward 3DGS methods under sparse causal inputs.<n>StreamSplat scales to long input streams with 256, 512, and 1024 views where fixed-view baselines run out of memory.
• Score: 13.605490241534797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally. We present \emph{StreamSplat}, a streaming feed-forward 3DGS framework that incrementally maintains a persistent geometry-grounded scene state and decodes it into renderable 3D Gaussians after each input chunk. StreamSplat centers on a \textbf{Voxel-Aligned Causal Cache (VACC)}, which stores historical 3D tokens in a memory-bounded voxel structure so that memory grows with explored scene geometry rather than stream length. To better reuse history during causal prediction, we introduce \textbf{History-Projected Depth Anchoring (HPDA)} to project cached geometry as depth guidance for current cost-volume estimation, and \textbf{Cache-Guided Feature Injection (CGFI)} to inject cached latent evidence into Gaussian-token regression. Experiments on DL3DV, RealEstate10K, and ScanNet show that StreamSplat remains competitive with state-of-the-art feed-forward 3DGS methods under sparse causal inputs, despite not using future views or full-scene context. More importantly, it scales to long input streams with 256, 512, and 1024 views where fixed-view baselines run out of memory, yielding sustained improvements in novel-view synthesis quality as more observations arrive. The code will be made publicly available upon acceptance.

Related papers

• FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation [72.38727895659405]
  We introduce FLAT, which decodes triangle splats directly from video diffusion latents.<n>On standard benchmarks, FLAT achieves significantly better geometric accuracy compared to state-of-the-art feedforward baselines.<n>We show that a lightweight test-time refinement step converts the predicted triangle soup into a fully opaque, game-engine-ready representation.
  arXiv  Detail & Related papers  (2026-06-23T17:53:41Z)
• Stream3D: Sequential Multi-View 3D Generation via Evidential Memory [20.313446116978586]
  Stream3D is a training-free streaming mechanism that turns a frozen view-conditioned 3D generator into a streaming generator with constant cross-chunk memory.<n> evaluated on both realistic and synthetic streaming benchmarks.
  arXiv  Detail & Related papers  (2026-05-20T17:55:16Z)
• GSStream: 3D Gaussian Splatting based Volumetric Scene Streaming System [52.652341168561016]
  We propose GSStream, a novel volumetric scene streaming system to support 3DGS data format.<n> GSStream integrates a collaborative viewport prediction module to better predict users' future behaviors.<n>Our proposed GSStream system outperforms existing representative volumetric streaming systems in visual quality and network usage.
  arXiv  Detail & Related papers  (2026-03-10T14:25:00Z)
• Triangle Splatting+: Differentiable Rendering with Opaque Triangles [54.18495204764292]
  We introduce Triangle Splatting+, which directly optimize triangles within a differentiable splatting framework.<n>Our method surpasses prior splatting approaches in visual fidelity while remaining efficient and fast to training.<n>The resulting semi-connected meshes support downstream applications such as physics-based simulation or interactive walkthroughs.
  arXiv  Detail & Related papers  (2025-09-29T17:43:46Z)
• Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting [57.43483622778394]
  We introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer.<n>With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes.
  arXiv  Detail & Related papers  (2025-06-05T17:58:23Z)
• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views [68.94737256959661]
  AnySplat is a feed forward network for novel view synthesis from uncalibrated image collections.<n>A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance.<n>In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios.
  arXiv  Detail & Related papers  (2025-05-29T17:49:56Z)
• FlowR: Flowing from Sparse to Dense 3D Reconstructions [60.28571003356382]
  We propose a flow matching model that learns a flow to connect novel view renderings from possibly sparse reconstructions to renderings that we expect from dense reconstructions.<n>Our model is trained on a novel dataset of 3.6M image pairs and can process up to 45 views at 540x960 resolution (91K tokens) on one H100 GPU in a single forward pass.
  arXiv  Detail & Related papers  (2025-04-02T11:57:01Z)
• MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views [27.47491233656671]
  Novel View Synthesis (NVS) is a significant challenge in 3D vision applications. We propose textbfMVPGS, a few-shot NVS method that excavates the multi-view priors based on 3D Gaussian Splatting. Experiments show that the proposed method achieves state-of-the-art performance with real-time rendering speed.
  arXiv  Detail & Related papers  (2024-09-22T05:07:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.