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 171–180 of 514 papers

TitleStatusHype
A survey of synthetic data augmentation methods in computer vision—0
Voxel-Mesh Hybrid Representation for Real-Time View Synthesis—0
DNAct: Diffusion Guided Multi-Task 3D Policy Learning—0
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint VideosCode3
Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding—0
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage GenerationCode1
GaussianPro: 3D Gaussian Splatting with Progressive PropagationCode1
Flexible Physical Camouflage Generation Based on a Differential Approach—0
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian SplattingCode5
Neural Rendering based Urban Scene Reconstruction for Autonomous Driving—0
Show:102550
← PrevPage 18 of 52Next →

No leaderboard results yet.