HyperAI초신경
홈
뉴스
최신 연구 논문
튜토리얼
데이터셋
백과사전
SOTA
LLM 모델
GPU 랭킹
컨퍼런스
전체 검색
소개
한국어
HyperAI초신경
Toggle sidebar
전체 사이트 검색...
⌘
K
홈
SOTA
Novel View Synthesis
Novel View Synthesis On Tanks And Temples
Novel View Synthesis On Tanks And Temples
평가 지표
LPIPS
PSNR
SSIM
평가 결과
이 벤치마크에서 각 모델의 성능 결과
Columns
모델 이름
LPIPS
PSNR
SSIM
Paper Title
Repository
Mip-NERF 360
0.28
19.65
0.731
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
TensoRF + NeRFLiX
-
28.94
0.93
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
Plenoxels + NeRFLiX
-
28.61
-
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
Self-Organizing Gaussians
0.208
25.63
-
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
TensoRF + NeRFLiX++
-
29.24
-
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm
-
Compact3D
0.188
23.47
0.840
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
3D Gaussian Splatting
0.183
23.14
0.841
3D Gaussian Splatting for Real-Time Radiance Field Rendering
DIVeR + NeRFLiX
-
-
0.924
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
C3DGS
0.201
0.2332
0.831
Compact 3D Gaussian Representation for Radiance Field
-
HAC 3DGS
0.177
24.40
0.853
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
0 of 10 row(s) selected.
Previous
Next