arXiv Computer Vision
Fovea-JEPA: Overcoming Geometric Blind Spots in V-JEPA for Camera Motion Recognition
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
Oct 16
DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language Models
DK‑VLM introduces Dual‑Kernel Attention, where a visual token’s attention is computed from both its input position and its geometric position derived from 3D points and camera poses. A semantic kernel preserves pretrained attention while a geometric kernel modulates attention via point displacements and relative view transformations, with a learned gate fusing the two. The model also employs Reference‑Frame Composition supervision to update its reference frame across successive judgments, achieving top scores on six spatial benchmarks and strong performance on VSI‑Bench and ReVSI‑32.
arXiv Computer Vision
Sep 2
CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling
CameraEditor is a new framework that transforms camera-controlled image editing into a temporal sequence prediction problem. By using video diffusion models, it incorporates a geometric perception module and dynamic reference routing to create precise visual references through dynamic panorama cropping. The method also inserts intermediate transition frames to handle large perspective shifts, maintaining content identity and spatial coherence, and is evaluated on a dataset of 5,760 instances with a benchmark of 462 test cases, achieving state‑of‑the‑art performance.
arXiv AI
Aug 12
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
arXiv:2608. 10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation.
arXiv AI
Sep 21
FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models
FOCAL‑VLA is a framework that improves vision‑language‑action models by combining subtask‑guided geometry distillation with implicit world modeling. It transfers geometric knowledge from VGGT to focus on subtask‑relevant image regions and uses Track4World features to capture future 3D evolution, guiding action generation without running these models at inference time. Experiments demonstrate that FOCAL‑VLA outperforms baselines on both simulation benchmarks and real‑world manipulation tasks.
arXiv AI
Jun 11
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
arXiv:2606. 11683v1 Announce Type: cross Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory.
arXiv Computer Vision
Sep 2
Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models
arXiv:2609.01059v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. How...