arXiv Computer Vision
Aug 27

Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging

The paper introduces a structure‑aware merging pipeline that consolidates per‑pixel 3D Gaussian primitives from any feed‑forward reconstruction method into a compact, content‑adaptive Gaussian set. By grouping spatially coherent Gaussians with adaptive superpixel segmentation guided by a saliency map, compressing clusters via a learned encoder, and merging representations across views using geometric overlap and feature similarity, the method reduces the number of Gaussians to about one‑twentieth of the original while preserving visual quality. A level‑of‑detail decoder allows controllable resolution, and the pipeline operates as a backbone‑agnostic post‑processing module, improving robustness and rendering efficiency.

By Tim-Felix Fassch, Jochen Kall, Cyrill Stachniss
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
6d ago

RetinexGS: Retinex-Inspired Gaussian Splatting for Low-Light RAW Reconstruction

RetinexGS is a RAW-domain 3D Gaussian Splatting framework that improves low-light novel-view synthesis by combining Retinex-inspired appearance modeling with sensor-informed optimization. It factorizes each Gaussian’s color into a view-independent base color and a shared, position- and view-dependent modulation field, regularizing them separately to handle noisy observations. Using DNG noise metadata to weight the reconstruction loss and depth-guided initialization, RetinexGS outperforms LE3D and RawNeRF by 2.18 dB and 2.71 dB in mean sRGB PSNR across five scenes while enabling real-time rendering.

By Yulang Fei, Huaiyuan Weng, Chul Min Yeum
Hugging Face Trending Papers
Jul 27

GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion

Feed-forward 3D Gaussian Splatting (3DGS) enables scalable scene reconstruction without per-scene optimization, yet produces dense Gaussians that are costly to store and transmit. Existing feed-forward Gaussian compression methods formulate decoding as deterministic representation recovery, which becomes inadequate at low bitrates when high-frequency textures and view-dependent appearance are discarded.