MVGSR: Multi-View Consistent 3D Gaussian Super-Resolution via Epipolar Guidance
- URL: http://arxiv.org/abs/2512.15048v1
- Date: Wed, 17 Dec 2025 03:23:12 GMT
- Title: MVGSR: Multi-View Consistent 3D Gaussian Super-Resolution via Epipolar Guidance
- Authors: Kaizhe Zhang, Shinan Chen, Qian Zhao, Weizhan Zhang, Caixia Yan, Yudeng Xin,
- Abstract summary: We introduce Multi-View Consistent 3D Gaussian Splatting Super-Resolution (MVGSR)<n>MVGSR focuses on integrating multi-view information for 3DGS rendering with high-frequency details and enhanced consistency.<n>Our method achieves state-of-the-art performance on both object-centric and scene-level 3DGS SR benchmarks.
- Score: 13.050002358238793
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Scenes reconstructed by 3D Gaussian Splatting (3DGS) trained on low-resolution (LR) images are unsuitable for high-resolution (HR) rendering. Consequently, a 3DGS super-resolution (SR) method is needed to bridge LR inputs and HR rendering. Early 3DGS SR methods rely on single-image SR networks, which lack cross-view consistency and fail to fuse complementary information across views. More recent video-based SR approaches attempt to address this limitation but require strictly sequential frames, limiting their applicability to unstructured multi-view datasets. In this work, we introduce Multi-View Consistent 3D Gaussian Splatting Super-Resolution (MVGSR), a framework that focuses on integrating multi-view information for 3DGS rendering with high-frequency details and enhanced consistency. We first propose an Auxiliary View Selection Method based on camera poses, making our method adaptable for arbitrarily organized multi-view datasets without the need of temporal continuity or data reordering. Furthermore, we introduce, for the first time, an epipolar-constrained multi-view attention mechanism into 3DGS SR, which serves as the core of our proposed multi-view SR network. This design enables the model to selectively aggregate consistent information from auxiliary views, enhancing the geometric consistency and detail fidelity of 3DGS representations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both object-centric and scene-level 3DGS SR benchmarks.
Related papers
- SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting [13.122286465610323]
3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images.<n>Existing methods rely on dense LR inputs and per-scene optimization.<n>We introduce SR3R, a feed-forward framework that directly predicts HR 3DGS representations from sparse LR views.
arXiv Detail & Related papers (2026-02-27T13:45:22Z) - One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion [57.824020826432815]
We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images.<n>We design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone.<n>We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process.
arXiv Detail & Related papers (2026-01-20T17:11:55Z) - SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting [50.36978600976209]
A natural strategy is to apply super-resolution (SR) to low-resolution (LR) input views, but independently enhancing each image introduces multi-view inconsistencies.<n>We propose SplatSuRe, a method that selectively applies SR content only in undersampled regions lacking high-frequency supervision.<n>Across Tanks & Temples, Deep Blending and Mip-NeRF 360, our approach surpasses baselines in both fidelity and perceptual quality.
arXiv Detail & Related papers (2025-12-01T20:08:39Z) - SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images [22.87137082795346]
We propose textbfSRSplat, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views.<n>Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues.
arXiv Detail & Related papers (2025-11-15T05:17:44Z) - BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation [70.27358326228399]
We propose a BasicAVSR for Arbitrary-scale video super-resolution (AVSR)<n>AVSR aims to enhance the resolution of video frames, potentially various scaling factors.<n>We show that BasicAVSR significantly outperforms existing methods in terms of super-resolution quality, generalization ability, and inference speed.
arXiv Detail & Related papers (2025-10-30T05:08:45Z) - RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions [67.48495052903534]
We propose a general and efficient multi-view feature enhancement module, RobustGS.<n>It substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions.<n>The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner.
arXiv Detail & Related papers (2025-08-05T04:50:29Z) - SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting [6.309174895120047]
3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality.<n>However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the coarse nature of primitives derived from low-resolution input views.<n>We propose SuperGS, an expansion of Scaffold-GS designed with a two-stage coarse-to-fine training framework.
arXiv Detail & Related papers (2025-05-24T11:33:57Z) - CrossView-GS: Cross-view Gaussian Splatting For Large-scale Scene Reconstruction [5.528874948395173]
We propose a novel cross-view Gaussian Splatting method for large-scale scene reconstruction based on multi-branch construction and fusion.<n>Our method achieves superior performance in novel view synthesis compared to state-of-the-art methods.
arXiv Detail & Related papers (2025-01-03T08:24:59Z) - FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction [69.63414788486578]
FreeSplatter is a scalable feed-forward framework that generates high-quality 3D Gaussians from uncalibrated sparse-view images.<n>Our approach employs a streamlined transformer architecture where self-attention blocks facilitate information exchange.<n>We develop two specialized variants--for object-centric and scene-level reconstruction--trained on comprehensive datasets.
arXiv Detail & Related papers (2024-12-12T18:52:53Z) - S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR)
Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection.
In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
arXiv Detail & Related papers (2024-02-22T11:40:49Z)
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.