StereoSplat+: Feed-Forward Stereo Gaussian Splatting with Diffusion-Assisted Progressive Inference

• URL: http://arxiv.org/abs/2607.08808v1
• Date: Thu, 09 Jul 2026 16:32:45 GMT
• Title: StereoSplat+: Feed-Forward Stereo Gaussian Splatting with Diffusion-Assisted Progressive Inference
• Abstract summary: 3D Gaussian Splatting (3DGS) has enabled high-quality, render-ready scene representations for novel-view synthesis.<n>Most existing 3DGS pipelines rely on multi-view observations to achieve sufficient coverage.<n>We present StereoSplat+, a diffusion-enhanced feed-forward framework that enables causal reconstruction from a single stereo pair.
• Score: 18.13347835114754
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled high-quality, render-ready scene representations for novel-view synthesis. However, most existing 3DGS pipelines rely on multi-view observations (or non-causal access to future frames) to achieve sufficient coverage, which is often unavailable in on-device robotics and AR settings where sensing is restricted to a single stereo rig. Recovering a high-quality 3DGS scene from one stereo observation, therefore, remains challenging due to occlusions, limited field of view, and missing geometry. We present StereoSplat+, a diffusion-enhanced feed-forward framework that enables causal reconstruction from a single stereo pair. Our method builds on two key components. First, we propose StereoSplat, an input-invariant feed-forward 3D Gaussian estimator that takes a variable number of posed stereo pairs as input and predicts high-quality 3D Gaussians. StereoSplat fuses complementary geometry cues via a cost-volume branch and a triplane-based 3D volume branch and leverages continuous pose encoding to generalize across view counts and camera configurations. Second, since multiple posed stereo pairs are typically unavailable at inference time, we introduce a diffusion-enhanced one-shot progressive inference scheme called StereoSplat+: starting from one stereo pair, we render novel stereo views from the predicted 3DGS, refine them with a one-step diffusion enhancer, and feed them back as additional inputs to update the 3DGS. Experiments on the KITTI-360 dataset show that StereoSplat+ improves novel-view rendering quality and geometry accuracy, especially in occluded regions and under strong view extrapolation, outperforming recent feed-forward 3DGS baselines.

Related papers

• PointSplat: Compact Gaussian Splatting via Human-Centric Prediction [70.45838533838104]
  We propose PointSplat, a novel human-centric approach to producing 3D human representations from input views on the fly.<n>The proposed method first estimates a coarse geometric proxy and performs ray casting to prune redundant points.<n>It then employs a Point-Image Transformer to fuse appearance and geometry features, predicting Gaussian attributes in a single forward pass.
  arXiv  Detail & Related papers  (2026-06-30T17:59:05Z)
• StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors [0.9326260051834822]
  3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis.<n>It suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints.<n>We propose StereoGS, a novel sparse-view 3DGS framework that integrates stereo priors to establish reliable binocular consistency.
  arXiv  Detail & Related papers  (2026-06-29T16:45:57Z)
• Stereo World Model: Camera-Guided Stereo Video Generation [52.3922115596956]
  We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.<n>Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity.
  arXiv  Detail & Related papers  (2026-03-18T05:42:22Z)
• PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting [4.451779041553596]
  3D Gaussian splatting (3DGS) is an innovative rendering technique that surpasses the neural radiance field (NeRF) in both rendering speed and visual quality.<n>We propose a Point-wise Feature-Aware Gaussian Splatting framework that enables real-time, high-quality rendering from sparse training views.
  arXiv  Detail & Related papers  (2025-06-12T04:07:07Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis [25.924727931514735]
  Generalizable 3DGS can reconstruct new scenes from sparse-view observations in a feed-forward inference manner. Existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes. We propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis.
  arXiv  Detail & Related papers  (2024-10-30T08:51:29Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes [50.534213038479926]
  FreeSplat is capable of reconstructing geometrically consistent 3D scenes from long sequence input towards free-view synthesis. We propose a simple but effective free-view training strategy that ensures robust view synthesis across broader view range regardless of the number of views.
  arXiv  Detail & Related papers  (2024-05-28T08:40:14Z)
• Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion [45.171150395915056]
  3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to predict accurate semantic scenes due to inherent geometric ambiguity and incomplete observations. We resort to stereo matching technique and bird's-eye-view (BEV) representation learning to address such issues in SSC.
  arXiv  Detail & Related papers  (2023-03-24T12:33:44Z)
• DSGN++: Exploiting Visual-Spatial Relation forStereo-based 3D Detectors [60.88824519770208]
  Camera-based 3D object detectors are welcome due to their wider deployment and lower price than LiDAR sensors. We revisit the prior stereo modeling DSGN about the stereo volume constructions for representing both 3D geometry and semantics. We propose our approach, DSGN++, aiming for improving information flow throughout the 2D-to-3D pipeline.
  arXiv  Detail & Related papers  (2022-04-06T18:43:54Z)

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.