HyperAIHyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAIHyperAI

Novel View Synthesis On Tanks And Temples

المقاييس

LPIPS
PSNR
SSIM

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
LPIPS
PSNR
SSIM
Paper TitleRepository
Mip-NERF 3600.2819.650.731Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields-
TensoRF + NeRFLiX-28.940.93NeRFLiX: 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 Gaussians0.20825.63-Compact 3D Scene Representation via Self-Organizing Gaussian Grids-
TensoRF + NeRFLiX++-29.24-From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm-
Compact3D0.18823.470.840CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization-
3D Gaussian Splatting0.18323.140.8413D Gaussian Splatting for Real-Time Radiance Field Rendering-
DIVeR + NeRFLiX--0.924NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer-
C3DGS0.2010.23320.831Compact 3D Gaussian Representation for Radiance Field-
HAC 3DGS0.17724.400.853HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression-
0 of 10 row(s) selected.
Novel View Synthesis On Tanks And Temples | SOTA | HyperAI