arXiv:2609.12682v1 Announce Type: new
Abstract: Reconstructing 3D scenes under real-world low-light conditions remains challenging due to severe sensor noise, low signal-to-noise ratios, and degraded...
By Shaurya Pavan A, Vemunuri Divya Madhuri, Yash Pradeep Gawande, Kaushik Mitra
SteadySplats introduces a method to reduce high‑frequency noise in stochastic rendering of 3D Gaussian Splatting models. The approach combines a history‑based spatial resampling scheme for faster image convergence, temporal importance resampling for camera‑movement coherence, and a color regularizer during training to lower variance along view rays. The resulting Vulkan‑based renderer achieves a 13 dB PSNR improvement over prior stochastic methods at one sample per pixel and converges quickly to a low‑error sorted 3DGS representation.
By Felix Windisch, Thomas K\"ohler, Lukas Radl, Chris Wyman, Georgios Kopanas, Bernhard Kerbl, Markus Steinberger
Naka-GS is a low‑light 3D Gaussian Splatting framework that jointly enhances observations and improves Gaussian initialization. It introduces Naka‑Guided Chroma Correction, which uses a fixed bionic response as a photometric anchor to learn bounded, frequency‑decoupled luminance and chromatic corrections, preserving fine structures while reducing color and boundary artifacts. A lightweight, non‑learned Point‑Prior Compaction Module refines dense scene priors via voxel pooling and distance‑adaptive pruning, cutting the number of points from 1.00 M to 59.52 K and shortening optimization time by 37.7 % while achieving state‑of‑the‑art PSNR, SSIM, and LPIPS on eight RealX3D scenes.
By Runyu Zhu, SiXun Dong, Zhiqiang Zhang, Qingxia Ye, Rongjun Qin, Zhihua Xu
arXiv:2610.07958v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
By Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
arXiv:2611.17957v1 Announce Type: new
Abstract: Arbitrary-scale light field spatial super-resolution reconstructs high-resolution views at any requested scale from low-resolution multi-view observati...
By Zeqiang Wei, Angulia Yang, Min Xu
WilLaGS introduces a unified framework that enhances 3D Gaussian Splatting for in-the-wild scenes by learning a continuous global appearance manifold with a β‑VAE and generating dynamic Tri‑Plane features for spatially‑varying local illumination. It also incorporates a self‑supervised perceptual masking mechanism using a Teacher‑Student EMA architecture to suppress transient artifacts and identify inconsistent regions. Experiments on multiple datasets show that WilLaGS achieves state‑of‑the‑art reconstruction quality and novel view synthesis while preserving real‑time rendering efficiency.
By Yuhao Bai, Qianqiu Tan, Lilong Chen, Huanhuan Lv, Lijun Chen
arXiv:2609.01516v1 Announce Type: new
Abstract: While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor...
By Qian Wang, Yu Wang, Weiqi Li, Xinhua Cheng, Xiandong Meng, Ronggang Wang, Jian Zhang
arXiv:2608.23549v1 Announce Type: new
Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
By Khiem Vuong, Deva Ramanan, Srinivasa Narasimhan
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
The paper presents DIRT, a live novel-view synthesis method that uses depth-completed image-based rendering with a two-band blending strategy. It operates on a posed set of depth sensor observations and images, completing a sparsely filled depth buffer in screen space and fusing projected images without any neural networks or scene-specific optimization. The approach is non‑neural, training‑free, and works across heterogeneous sensors such as RGB‑D cameras, LiDAR, and thermal cameras, achieving lower latency and competitive performance in both live and conventional NVS benchmarks.
By Mathias Harrer, Laura Fink, Noah Lewis, Paul Himmler, Tim Weyrich
arXiv:2609.13262v1 Announce Type: new
Abstract: 3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exh...
By Yunlai Zhou, Yiren Lu, Tuo Liang, Disheng Liu, Vipin Chaudhary, Yu Yin
arXiv:2609.36969v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) is a state-of-the-art technique for 3D scene rendering, offering high efficiency and excellent visual quality. However, be...
By Gyeonggwan Lee, Seunghwan Hong, Junghun Suh