GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.
Pixel-perfect depth with semantics-prompted diffusion transformers.arXiv preprint arXiv:2510.07316, 2025a
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal video generation.
WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.
citing papers explorer
-
GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal video generation.
-
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.