arXiv Computer Vision
MAGIC: Learning from Visibility Asymmetry for Unsupervised Stereo Matching
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 23
SAMatcher: Dense Co-Visibility Modeling via Cross-View Fusion for Scale-Imbalance Image Matching
arXiv:2606.03406v2 Announce Type: replace Abstract: Reliable correspondence estimation supports image processing and 3D vision tasks, including Structure from Motion, visual localization, and image r...
Hugging Face Trending Papers
Jul 5
AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation
Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching.
arXiv Computer Vision
Sep 2
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
arXiv:2609.01530v1 Announce Type: new Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the refere...
arXiv Computer Vision
Sep 25
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
The paper introduces OVIE, a monocular novel-view synthesis method that eliminates the need for multi‑view training data. By using a frozen depth estimator to generate pseudo‑target views from single images and applying masked and adversarial losses, OVIE is trained on 30 million uncurated images. It achieves state‑of‑the‑art performance on RealEstate10K and DL3DV, produces highly consistent multi‑view trajectories, and runs at 116 FPS—over 600× faster than the fastest baseline.
arXiv Computer Vision
2d ago
Depth-to-RGB: Repurposing a Frozen Depth Estimator for Geometry-Guided Compositing
arXiv:2610.09125v1 Announce Type: new Abstract: Reference-based object compositing inserts or replaces an object using a background image, a reference image, and a 2D compositing mask. These inputs g...
arXiv Computer Vision
Sep 1
PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching
arXiv:2608.29819v1 Announce Type: new Abstract: Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues ar...