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.
Pytorch: An im- perative style, high-performance deep learning library.Ad- vances in neural information processing systems, 32
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
UniDAC achieves universal metric depth estimation across camera types by decoupling relative depth prediction from spatially varying scale estimation using a depth-guided module and distortion-aware positional embedding.
G-MIXER achieves state-of-the-art zero-shot composed image retrieval by using geodesic mixup to build diverse implicit candidates and MLLM-derived explicit semantics for re-ranking.
ELiC delivers state-of-the-art real-time LiDAR geometry compression by propagating features across bit depths, selecting from a bag of encoders, and preserving Morton order.
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.
-
UniDAC: Universal Metric Depth Estimation for Any Camera
UniDAC achieves universal metric depth estimation across camera types by decoupling relative depth prediction from spatially varying scale estimation using a depth-guided module and distortion-aware positional embedding.
-
G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion and Explicit Semantic Re-ranking for Zero-Shot Composed Image Retrieval
G-MIXER achieves state-of-the-art zero-shot composed image retrieval by using geodesic mixup to build diverse implicit candidates and MLLM-derived explicit semantics for re-ranking.
-
ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders
ELiC delivers state-of-the-art real-time LiDAR geometry compression by propagating features across bit depths, selecting from a bag of encoders, and preserving Morton order.