相关论文: ReDepth Anything: Test-Time Depth Refinement via S…

We present a fast and accurate method for dense depth reconstruction from sparsely sampled light fields obtained using a synchronized camera array. In our method, the source images are over-segmented into non-overlapping compact superpixels…

Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error…

We propose an embarrassingly simple but very effective scheme for high-quality dense stereo reconstruction: (i) generate an approximate reconstruction with your favourite stereo matcher; (ii) rewarp the input images with that approximate…

Depth estimation from a single image represents a fascinating, yet challenging problem with countless applications. Recent works proved that this task could be learned without direct supervision from ground truth labels leveraging image…

Zero-shot depth estimation (DE) models exhibit strong generalization performance as they are trained on large-scale datasets. However, existing models struggle with high-resolution images due to the discrepancy in image resolutions of…

Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its success, it remains an open question regarding DAMs' performance…

Photometric stereo, a problem of recovering 3D surface normals using images of an object captured under different lightings, has been of great interest and importance in computer vision research. Despite the success of existing traditional…

Depth guided any-to-any image relighting aims to generate a relit image from the original image and corresponding depth maps to match the illumination setting of the given guided image and its depth map. To the best of our knowledge, this…

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…

Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely…

We present a self-supervised learning-based pipeline for dense 3D reconstruction from full-length monocular endoscopic videos without a priori modeling of anatomy or shading. Our method only relies on unlabeled monocular endoscopic videos…

Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…

Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion-based test-time optimization, which is…

A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image…

Commercial RGB-D cameras often produce noisy, incomplete depth maps for non-Lambertian objects. Traditional depth completion methods struggle to generalize due to the limited diversity and scale of training data. Recent advances exploit…

State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in…

Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning universal representations and the severe lack of labeled…

In this study, we propose a simple and effective fine-tuning algorithm called "restore-from-restored", which can greatly enhance the performance of fully pre-trained image denoising networks. Many supervised denoising approaches can produce…