works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.CV2026

Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splatting

Neel Kelkar, Simon Niedermayr, Kaloian Petkov +2

The paper presents a method that separates low‑frequency geometry and view‑dependent appearance from high‑frequency texture using 2D surfels and a baked spatial hash‑grid texture a…

cs.CV2026

Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting

Neel Kelkar, Simon Niedermayr, Klaus Engel +1

We introduce a hybrid Gaussian-hash-grid radiance representation for reconstructing 2D Gaussian scene models from multi-view images. Similar to NeST splatting, our approach reduces…

cs.CV2026

MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion

Xuyang Chen, Zhijun Zhai, Kaixuan Zhou +9

Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban navigation and autonomous…

cs.CV2025

Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes

Shaoxiang Wang, Shihong Zhang, Christen Millerdurai +3

Despite recent advances in single-object front-facing inpainting using NeRF and 3D Gaussian Splatting (3DGS), inpainting in complex 360° scenes remains largely underexplored. This…

cs.CV2025

Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images

Simon Niedermayr, Christoph Neuhauser Rüdiger Westermann

We introduce an image upscaling technique tailored for 3D Gaussian Splatting (3DGS) on lightweight GPUs. Compared to 3DGS, it achieves significantly higher rendering speeds and red…