Related papers: LoftUp: Learning a Coordinate-Based Feature Upsamp…

Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver…

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can…

A typical 2D-to-3D pipeline takes multi-view images as input, where a Vision Foundation Model (VFM) extracts features that are spatially upsampled to dense representations for 3D reconstruction. If dense features across views preserve…

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

Depth estimation is a foundational component for 3D reconstruction in minimally invasive endoscopic surgeries. However, existing monocular depth estimation techniques often exhibit limited performance to the varying illumination and complex…

Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts. Instead of designing prompts manually, Context Optimization (CoOp) has been…

Stereo matching has become a key technique for 3D environment perception in intelligent vehicles. For a considerable time, convolutional neural networks (CNNs) have remained the mainstream choice for feature extraction in this domain.…

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying…

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability…

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…

Vision-language foundation models like CLIP have shown impressive zero-shot generalization, but finetuning on downstream datasets can cause overfitting and loss of its generalization ability on unseen domains. Although collecting additional…

This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFMs are widely employed in both conditional and unconditional…

Camouflaged image generation is emerging as a solution to data scarcity in camouflaged vision perception, offering a cost-effective alternative to data collection and labeling. Recently, the state-of-the-art approach successfully generates…

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 Models demonstrate…

We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. Second-order features are commonly used in dense prediction to build adjacent relations with a…

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…