arXiv Computer Vision
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
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
1d ago
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models
arXiv:2608.10708v2 Announce Type: replace Abstract: Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving...
arXiv AI
Jun 15
Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders
arXiv:2503. 19947v2 Announce Type: replace-cross Abstract: Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support.
arXiv AI
Jul 13
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
arXiv:2607. 09503v1 Announce Type: cross Abstract: A fundamental challenge in 3D reconstruction and robotic localization is co-visibility: determining which image pairs share overlapping visible surfaces, particularly in scenarios with minimal overlap.
arXiv AI
Aug 11
Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real
arXiv:2608. 07579v1 Announce Type: cross Abstract: The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting; depth is available only for training and validation, so inference is RGB-only.
arXiv AI
Jul 2
Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences
arXiv:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.
arXiv AI
Aug 28
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.