arXiv:2606. 08132v1 Announce Type: cross Abstract: Vision Transformers operate on fixed patch grids, which can introduce phase-dependent instability for dense prediction: changing the patch partition can change the token evidence available to a pixel, especially near boundaries.
arXiv:2607. 28589v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices.
The paper introduces Transformer-Within-Transformer (TWT), a post‑hoc technique that merges contiguous redundant layers in Vision Transformers into a single surrogate layer. By doing so, TWT cuts both parameter count and inference compute while maintaining competitive performance on natural image tasks with only half the depth. In histopathology applications, TWT not only matches but sometimes surpasses the baseline model’s performance.
Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders practical applications. Recent works have focused on m...
Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity.
The paper introduces a top‑down framework for accurately locating athletes in metric world coordinates using a single calibrated broadcast frame. It presents three main contributions: a Boundary‑Aware Adaptive Tiling method that expands tile boundaries to avoid splitting athletes across tiles, a specialized two‑keypoint estimator based on RTMPose‑X for pelvis and ground projection points, and a deterministic lift of 2D projections into 3D world coordinates via camera‑calibrated ray casting. The approach achieves a LocSim score of 97.44 and an mAP of 0.9128, surpassing the baseline by over 21 % on a public test set.
arXiv:2610.21642v1 Announce Type: new Abstract: Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders pract...
GramLoop is a training‑free framework that enhances frozen DINOv3 dense‑prediction models under distribution shift by adding inference computation within the visual backbone. It replays a short transformer window and uses final‑layer cosine‑Gram consistency to control each replay, propagating proposals through the frozen suffix and accepting them via a patchwise gate. Across object detection and semantic segmentation tasks, GramLoop improves performance on all five shifted benchmarks, notably raising COCO‑O mAP by +0.252 and Effective Robustness by +0.250 while maintaining clean ADE20K accuracy.
arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...
arXiv:2610.08213v1 Announce Type: new Abstract: Fringe Projection Profilometry (FPP) requires precise system characterisation to achieve reliable three-dimensional (3D) reconstructions; however, char...
NaCR: Visual Localization via NeRF-aided Camera Ray Regression proposes a unified framework that integrates Neural Radiance Fields (NeRF) with Camera Ray Regression (CRR) to improve visual localization accuracy. The method enhances the CRR baseline with three simple improvements, augments training data by synthesizing novel views from a pre‑trained NeRF, and employs a closed‑loop supervision pipeline that back‑propagates photometric rendering errors to refine predicted camera rays. A two‑stage training curriculum ensures stable convergence, and experiments on indoor and outdoor benchmarks show competitive accuracy with validated component efficacy.
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.