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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 514 papers

TitleStatusHype
3DGEER: Exact and Efficient Volumetric Rendering with 3D GaussiansCode1
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views—0
UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors—0
PS4PRO: Pixel-to-pixel Supervision for Photorealistic Rendering and Optimization—0
RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global IlluminationCode4
GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View SynthesisCode0
From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation—0
EVA: Expressive Virtual Avatars from Multi-view Videos—0
SpNeRF: Memory Efficient Sparse Volumetric Neural Rendering Accelerator for Edge Devices—0
A Survey of 3D Reconstruction with Event Cameras: From Event-based Geometry to Neural 3D Rendering—0
Show:102550
← PrevPage 2 of 52Next →

No leaderboard results yet.