paper-with-me

Papers Feature Upsampling

“Feature Upsampling” 태그가 달린 논문 39편 · 필터 해제

RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation

2026-06-22 · Yuchuan Ding, Linfei Li, Lin Zhang, Ying Shen arxiv

Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or pooled outputs are …

Feature Upsampling

ViT-Up: Faithful Feature Upsampling for Vision Transformers

2026-06-12 · Krispin Wandel, Jingchuan Wang, Hesheng Wang arxiv

Vision Transformers (ViTs) have become a dominant architecture for visual representation learning, providing exceptionally strong and broadly reusable backbone features. However, ViTs are commonly operated on relatively …

Semantic correspondenceRepresentation LearningSemantic SegmentationFeature Upsampling

Weighted Reverse Convolution for Feature Upsampling

2026-05-17 · Wentong Li, Zhiyuan Qi, Zichen Zhao, Kai Zhang 외 arxiv

Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks requiring fine-grained localization, dense …

Video Object SegmentationComputational EfficiencyFeature UpsamplingDepth Estimation

DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery

2026-05-04 · Ryan Faulkenberry, Saurabh Prasad arxiv

The remote sensing (RS) domain suffers from a lack of densely labeled datasets, which are costly to obtain. Thus, models that can segment RS imagery well without supervised fine-tuning are valuable, but existing solution…

Open Vocabulary Semantic SegmentationFeature Upsampling

Frozen Vision Transformers for Dense Prediction on Small Datasets: A Case Study in Arrow Localization

2026-04-18 · Maxwell Shepherd arxiv

We present a system for automated detection, localization, and scoring of arrow punctures on 40\,cm indoor archery target faces, trained on only 48 annotated photographs (5{,}084 punctures). Our pipeline combines three c…

Feature Upsampling

HD-VGGT: High-Resolution Visual Geometry Transformer

2026-03-28 · Tianrun Chen, Yuanqi Hu, Yidong Han, Hanjie Xu 외 arxiv

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), …

Feature Upsampling3D Reconstruction

DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models

2026-03-13 · Xiaoqiong Liu, Heng Fan arxiv

Recently, feature upsampling has gained increasing attention owing to its effectiveness in enhancing vision foundation models (VFMs) for pixel-level understanding tasks. Existing methods typically rely on high-resolution…

Feature Upsampling

UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders

2026-01-25 · Matthew Walmer, Saksham Suri, Anirud Aggarwal, Abhinav Shrivastava arxiv

The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features…

Feature Upsampling

Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation

2026-01-03 · Tianheng Cheng, Xinggang Wang, Junchao Liao, Wenyu Liu arxiv

Semantic segmentation is a fundamental problem in computer vision and it requires high-resolution feature maps for dense prediction. Current coordinate-guided low-resolution feature interpolation methods, e.g., bilinear …

Semantic SegmentationFeature Upsampling

NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering

2025-11-23 · Loick Chambon, Paul Couairon, Eloi Zablocki, Alexandre Boulch 외 arxiv

Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off: classical filters are fast and broadly …

Feature UpsamplingImage Restoration

Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

2025-11-20 · Minseok Seo, Mark Hamilton, Changick Kim arxiv

We present \textbf{Upsample Anything}, a lightweight test-time optimization (TTO) framework that restores low-resolution features to high-resolution, pixel-wise outputs without any training. Although Vision Foundation Mo…

Semantic SegmentationFeature UpsamplingDepth Estimation

AnyUp: Universal Feature Upsampling

2025-10-14 · Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle 외 arxiv

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need t…

Feature Upsampling

Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation

2025-08-29 · Ronan Docherty, Antonis Vamvakeros, Samuel J. Cooper arxiv

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these…

Interactive SegmentationComputational EfficiencyFeature UpsamplingObject Detection

Towards Open-World Human Action Segmentation Using Graph Convolutional Networks

2025-07-01 · Hao Xing, Kai Zhe Boey, Gordon Cheng arxiv

Human-object interaction segmentation is a fundamental task of daily activity understanding, which plays a crucial role in applications such as assistive robotics, healthcare, and autonomous systems. Most existing learni…

Out-of-Distribution DetectionAction SegmentationFeature Upsampling

JAFAR: Jack up Any Feature at Any Resolution

2025-06-10 · Paul Couairon, Loick Chambon, Louis Serrano, Jean-Emmanuel Haugeard 외

Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to produce the high-resolution modalities requ…

Feature Upsampling

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation

2025-05-04 · Volodymyr Havrylov, Haiwen Huang, Dan Zhang, Andreas Geiger

Vision Foundation Models (VFMs) are large-scale, pre-trained models that serve as general-purpose backbones for various computer vision tasks. As VFMs' popularity grows, there is an increasing interest in understanding t…

BenchmarkingFeature UpsamplingInteractive SegmentationScene Understanding

LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

2025-04-18 · Haiwen Huang, Anpei Chen, Volodymyr Havrylov, Andreas Geiger 외

Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level underst…

Feature Upsampling

LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention

2024-11-29 · Zewen Du, Zhenjiang Hu, Guiyu Zhao, Ying Jin 외

Feature upsampling is an essential operation in constructing deep convolutional neural networks. However, existing upsamplers either lack specific feature guidance or necessitate the utilization of high-resolution featur…

Feature UpsamplingInstance Segmentationobject-detectionObject Detection+2

Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels

2024-10-29 · Ruigang Fu, Qingyong Hu, Xiaohu Dong, Yinghui Gao 외

As a fundamental operation in modern machine vision models, feature upsampling has been widely used and investigated in the literatures. An ideal upsampling operation should be lightweight, with low computational complex…

Feature Upsamplingobject-detectionObject Detection

EfficientCD: A New Strategy For Change Detection Based With Bi-temporal Layers Exchanged

2024-07-22 · Sijun Dong, Yuwei Zhu, Geng Chen, Xiaoliang Meng

With the widespread application of remote sensing technology in environmental monitoring, the demand for efficient and accurate remote sensing image change detection (CD) for natural environments is growing. We propose a…

Change DetectionFeature Upsampling
1–20 / 39 다음 →