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 110 of 514 papers

TitleStatusHype
Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head SynthesisCode11
Instant Neural Graphics Primitives with a Multiresolution Hash EncodingCode6
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian SplattingCode5
GPAvatar: Generalizable and Precise Head Avatar from Image(s)Code4
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D GaussiansCode4
Neuralangelo: High-Fidelity Neural Surface ReconstructionCode4
RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global IlluminationCode4
On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection StrategyCode3
3D Facial Expressions through Analysis-by-Neural-SynthesisCode3
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint VideosCode3
Show:102550
← PrevPage 1 of 52Next →

No leaderboard results yet.