arXiv Computer Vision

FrontierGS: Progressive View-Space Frontier Expansion for Sparse 3D Gaussian Splatting

arXiv Computer Vision
Sep 3

RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation

RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.

By Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang
arXiv AI
Sep 28

Spackle: Completing Large View Single Image NVS with Adaptive Gaussians

Spackle is a lightweight residual learning framework designed to improve large-view single-image novel view synthesis (NVS) by mitigating capacity competition in hybrid decoupled systems that combine 3D Gaussian Splatting (3DGS) and diffusion models. It operates in three stages: predicting base 3DGS attributes, automatically identifying poorly reconstructed regions, and learning a residual 3DGS focused on those areas. During inference, Spackle merges the baseline and augmented Gaussians to produce high-fidelity novel views, achieving state‑of‑the‑art performance on large-view-deviation cases.

By Xuanzhi Liu, Yuhe Zhou, Xinyi Wu, Zhenyao Wu, Jinghao Chen, Ruize Han, Song Wang
arXiv Computer Vision
Oct 28

GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

GeoGSplat introduces a geometry‑grounded, feed‑forward Gaussian splatting framework that avoids the pixel‑aligned prediction bottleneck by using a fixed number of Gaussians. A dual‑branch encoder builds coarse 3D anchors and fine triplane features, while a hierarchical decoder progressively generates dense 3D points and Gaussian primitives for reconstruction and novel view synthesis. The method outperforms state‑of‑the‑art pixel‑aligned and non‑pixel‑aligned splatting techniques on DTU and NRGBD datasets, especially when rendering views far from the input cameras.

By Jiale Wang, Chen Zhao, Haoyang Zhang, Yanhao Wu, Fei He, Yanhu Shan, Rui Wu, Wei Ke, Tong Zhang
Hugging Face Trending Papers
Oct 29

ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting

ACD-GS introduces an Asymmetric Curvature-aware Densification framework for 3D Gaussian Splatting that uses second-order depth responses to guide cloning and splitting, thereby better capturing geometric discontinuities. It incorporates a multi-view photometric consistency constraint and a capacity-aware adaptive regulation strategy to balance densification and pruning during training. The approach reduces Gaussian count and storage by nearly 60% while maintaining competitive rendering fidelity, outperforming existing methods across multiple datasets.

Hugging Face Trending Papers
Aug 3

D^2-4DGS: Dual-Depth Guided Sparse-Camera 4D Gaussian Splatting

Dynamic 4D Gaussian Splatting has emerged as an efficient representation for dynamic novel view synthesis through explicit scene modeling and real-time rendering. However, existing methods typically require dense multi-view videos for sufficient geometric constraints, making capture expensive and limiting sparse-camera deployment.