Self-supervised monocular depth estimation improves in low-texture regions by using distance transforms on jointly estimated pre-semantic contours to create more informative loss signals.
Mixed citations
Understanding ssim
Mixed citation behavior. Most common role is background (57%).
9
Pith papers citing it
Background
57% of classified citations
citation-role summary
background 3
method 2
baseline 1
other 1
citation-polarity summary
verdicts
UNVERDICTED 9representative citing papers
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
A depth-aware conditional diffusion model reconstructs high-resolution 3D ocean states from extremely sparse surface observations in the Gulf of Mexico.
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
FF3R unifies geometric and semantic 3D reconstruction in a single annotation-free feed-forward network trained solely via RGB and feature rendering supervision.
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.
citing papers explorer
-
Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks
Self-supervised monocular depth estimation improves in low-texture regions by using distance transforms on jointly estimated pre-semantic contours to create more informative loss signals.
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
Confidence-Based Mesh Extraction from 3D Gaussians
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
-
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
-
High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observations
A depth-aware conditional diffusion model reconstructs high-resolution 3D ocean states from extremely sparse surface observations in the Gulf of Mexico.
-
RefTon: Reference person shot assist virtual Try-on
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
-
FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views
FF3R unifies geometric and semantic 3D reconstruction in a single annotation-free feed-forward network trained solely via RGB and feature rendering supervision.
-
MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
-
Image-to-Video Diffusion: From Foundations to Open Frontiers
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.