HAD uses multi-view reasoning from a pre-trained feedforward NVS network to estimate and mask hallucination scores in diffusion priors, reducing artifacts and achieving SOTA novel view synthesis in sparse-view 3D reconstruction.
Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normaliza- tion
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
A selective regularization framework lets scale-ambiguous monocular depth priors improve Gaussian Splatting geometry and rendering by isolating and supervising only ill-posed regions.
FACT-GS allocates higher texture sampling density to high-frequency areas in 2D Gaussian Splatting through a learnable deformation field, recovering sharper details at the same parameter budget.
citing papers explorer
-
HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction
HAD uses multi-view reasoning from a pre-trained feedforward NVS network to estimate and mask hallucination scores in diffusion priors, reducing artifacts and achieving SOTA novel view synthesis in sparse-view 3D reconstruction.
-
In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting
A selective regularization framework lets scale-ambiguous monocular depth priors improve Gaussian Splatting geometry and rendering by isolating and supervising only ill-posed regions.
-
FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting
FACT-GS allocates higher texture sampling density to high-frequency areas in 2D Gaussian Splatting through a learnable deformation field, recovering sharper details at the same parameter budget.