SOTAVerified

Novel View Synthesis

Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.

See Wiki for more introductions.

The Synthesis method include: NeRF, MPI and so on.

( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )

Papers

Showing 110 of 1441 papers

TitleStatusHype
Physically Based Neural LiDAR ResimulationCode0
Cameras as Relative Positional Encoding0
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second0
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures0
Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering0
Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps0
Refine Any Object in Any SceneCode1
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding0
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance FieldsCode1
DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting0
Show:102550
← PrevPage 1 of 145Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TensoRF + NeRFLiX++PSNR29.24Unverified
2TensoRF + NeRFLiXPSNR28.94Unverified
3Plenoxels + NeRFLiXPSNR28.61Unverified
4Self-Organizing GaussiansPSNR25.63Unverified
5HAC 3DGSPSNR24.4Unverified
6Compact3DPSNR23.47Unverified
73D Gaussian SplattingPSNR23.14Unverified
8Mip-NERF 360PSNR19.65Unverified
9DIVeR + NeRFLiXSSIM0.92Unverified
10C3DGSPSNR0.23Unverified