HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Novel View Synthesis On Llff

평가 지표

LPIPS

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	LPIPS	PSNR	SSIM	Paper Title	Repository
NeRF	0.25	26.5	0.811	MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
AdaNeRF	-	25.7	-	HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
K-Planes (hybrid)	-	26.92	0.847	K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
HyperReel	-	26.2	-	HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
TermiNeRF	-	23.6	-	HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Plenoxels + NeRFLiX	0.156	26.9	0.864	NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
DoNeRF	-	22.9	-	HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Plenoxels	-	26.29	-	K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
SNeRG	0.183	25.63	0.818	MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
TensoRF	-	26.73	0.839	K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
JAXNeRF	0.173	26.92	0.831	MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
MobileNeRF	0.183	25.91	0.825	MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
K-Planes (explicit)	-	26.78	0.841	K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
Instant NGP	-	25.6	-	HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
TensoRF + NeRFLiX	0.149	27.39	0.867	NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer

0 of 15 row(s) selected.