SOTAVerified

Neural Rendering

Given a representation of a 3D scene of some kind (point cloud, mesh, voxels, etc.), the task is to create an algorithm that can produce photorealistic renderings of this scene from an arbitrary viewpoint. Sometimes, the task is accompanied by image/scene appearance manipulation.

Papers

Showing 3140 of 514 papers

TitleStatusHype
COLMAP-Free 3D Gaussian SplattingCode2
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category ReconstructionCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian SplatsCode2
Collaborative Neural Rendering using Anime Character SheetsCode2
Compressing Volumetric Radiance Fields to 1 MBCode2
BokehMe: When Neural Rendering Meets Classical RenderingCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
HUGS: Human Gaussian SplatsCode2
HF-NeuS: Improved Surface Reconstruction Using High-Frequency DetailsCode2
Show:102550
← PrevPage 4 of 52Next →

No leaderboard results yet.