Related papers: Upsample Anything: A Simple and Hard to Beat Basel…

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 to be re-trained for…

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 descriptors are…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

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 understanding. Feature…

The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since…

Downsampling is one of the most basic image processing operations. Improper spatio-temporal downsampling applied on videos can cause aliasing issues such as moir\'e patterns in space and the wagon-wheel effect in time. Consequently, the…

We present DySample, an ultra-lightweight and effective dynamic upsampler. While impressive performance gains have been witnessed from recent kernel-based dynamic upsamplers such as CARAFE, FADE, and SAPA, they introduce much workload,…

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream…

We propose a novel method of efficient upsampling of a single natural image. Current methods for image upsampling tend to produce high-resolution images with either blurry salient edges, or loss of fine textural detail, or spurious noise…

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. While super-resolution is widely used in…

Time-of-Flight (ToF) depth sensing camera is able to obtain depth maps at a high frame rate. However, its low resolution and sensitivity to the noise are always a concern. A popular solution is upsampling the obtained noisy low resolution…

There has been a lot of recent research on improving the efficiency of fine-tuning foundation models. In this paper, we propose a novel efficient fine-tuning method that allows the input image size of Segment Anything Model (SAM) to be…

In this paper, we present a novel upsampling framework to enhance the spatial resolution of the depth image. In our framework, the upscaling of a low-resolution depth image is guided by a corresponding intensity images, we formulate it as a…

Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data…

To handle the large scale of whole slide images in computational pathology, most approaches first tessellate the images into smaller patches, extract features from these patches, and finally aggregate the feature vectors with…

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource…

Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventionally requires parameter updates, with even…

Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision…

The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in…

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 required for downstream…