← Search

Ayush Saraf

7 accepted papers

2025

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

CVPR 2025poster

3D Gaussian Splatting (3DGS) has recently emerged as a state-of-the-art 3D reconstruction and rendering technique due to its high-quality results and fast training and rendering time. However, pixels covered by the same Gaussian are always shaded in the same color up to a Gaussian falloff scaling fa…

Cited by 3SourcePDFScholar
2024

LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering

CVPR 2024poster

Advancements in neural signed distance fields (SDFs) have enabled modeling 3D surface geometry from a set of 2D images of real-world scenes. Baking neural SDFs can extract explicit mesh with appearance baked into texture maps as neural features. The baked meshes still have a large memory footprint a…

Cited by 7SourcePDFScholar
2023

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

ICCV 2023poster

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals. Matting with associated effects such as shadows and reflections has also attracted increasing research activity, and methods like Omnimatte have been propos…

Cited by 7PDFcodeScholar
2023

Robust Dynamic Radiance Fields

CVPR 2023poster

Dynamic radiance field reconstruction methods aim to model the time-varying structure and appearance of a dynamic scene. Existing methods, however, assume that accurate camera poses can be reliably estimated by Structure from Motion (SfM) algorithms. These methods, thus, are unreliable as SfM algori…

2022

Boosting View Synthesis With Residual Transfer

CVPR 2022poster

Volumetric view synthesis methods with neural representations, such as NeRF and NeX, have recently demonstrated high-quality novel view synthesis. Optimizing these representations is slow, however, and even fully trained models cannot reproduce all fine details in the input views. We present a simpl…

Cited by 5PDFcodeScholar