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
RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global IlluminationCode4
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D GaussiansCode4
GPAvatar: Generalizable and Precise Head Avatar from Image(s)Code4
Neuralangelo: High-Fidelity Neural Surface ReconstructionCode4
SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous DrivingCode3
3D Facial Expressions through Analysis-by-Neural-SynthesisCode3
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D GenerationCode3
Show:102550
← PrevPage 1 of 52Next →

No leaderboard results yet.