相关论文: ECoDepth: Effective Conditioning of Diffusion Mode…

Depth completion, predicting dense depth maps from sparse depth measurements, is an ill-posed problem requiring prior knowledge. Recent methods adopt learning-based approaches to implicitly capture priors, but the priors primarily fit…

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various…

Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies…

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Monocular depth estimation has recently progressed beyond ordinal depth to provide metric depth predictions. However, its reliability in underwater environments remains limited due to light attenuation and scattering, color distortion,…

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…

Self-supervised depth estimation has shown its great effectiveness in producing high quality depth maps given only image sequences as input. However, its performance usually drops when estimating on border areas or objects with thin…

Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric…

Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself. However, some of the current methods tend to cheat from the background,…

In the area of self-supervised monocular depth estimation, models that utilize rich-resource inputs, such as high-resolution and multi-frame inputs, typically achieve better performance than models that use ordinary single image input.…

Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, while event cameras offer high dynamic range and temporal…

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in…

We introduce the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models. A growing research direction attempts to employ diffusion models to perform downstream vision tasks by exploiting their…

Diffusion models have quickly risen in popularity for their ability to model complex distributions and perform effective posterior sampling. Unfortunately, the iterative nature of these generative models makes them computationally expensive…

Single-image depth estimation is essential for endoscopy tasks such as localization, reconstruction, and augmented reality. Most existing methods in surgical scenes focus on in-domain depth estimation, limiting their real-world…

Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available. This paper proposes…

Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the…

Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…

Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However,…

Visual-semantic embedding models have been recently proposed and shown to be effective for image classification and zero-shot learning, by mapping images into a continuous semantic label space. Although several approaches have been proposed…