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 91100 of 514 papers

TitleStatusHype
LABELMAKER: Automatic Semantic Label Generation from RGB-D TrajectoriesCode1
CVTHead: One-shot Controllable Head Avatar with Vertex-feature TransformerCode1
VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural RenderingCode1
PoRF: Pose Residual Field for Accurate Neural Surface ReconstructionCode1
ResFields: Residual Neural Fields for Spatiotemporal SignalsCode1
TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving ScenariosCode1
NEnv: Neural Environment Maps for Global IlluminationCode1
PAPR: Proximity Attention Point RenderingCode1
EPIC Fields: Marrying 3D Geometry and Video UnderstandingCode1
DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric VoxelizationCode1
Show:102550
← PrevPage 10 of 52Next →

No leaderboard results yet.