Related papers: Towards Physically-Based Sky-Modeling For Image Ba…

Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccurate reconstructions that are sensitive to ambient illumination conditions. Here we…

This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR imaging, input images are first aligned using optical flows…

Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining physical plausibility, and the limited generalizability imposed by data-driven priors.…

Spherical coordinate systems, which are ubiquitous in astronomy, cannot be shown without distortion on flat, two-dimensional surfaces. This poses challenges for the two complementary phases of visual exploration -- making discoveries in…

We propose a physically-motivated deep learning framework to solve a general version of the challenging indoor lighting estimation problem. Given a single LDR image with a depth map, our method predicts spatially consistent lighting at any…

Neural Radiances Fields (NeRF) and their extensions have shown great success in representing 3D scenes and synthesizing novel-view images. However, most NeRF methods take in low-dynamic-range (LDR) images, which may lose details, especially…

Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently,…

Outdoor scene parsing models are often trained on ideal datasets and produce quality results. However, this leads to a discrepancy when applied to the real world. The quality of scene parsing, particularly sky classification, decreases in…

Hyperspectral image (HSI) analysis plays a critical role in remote sensing, agriculture, and environmental monitoring. However, traditional methods often struggle to handle the high dimensionality, spectral redundancy, and noise inherent in…

There are shadow and highlight regions in a low dynamic range (LDR) image which is captured from a high dynamic range (HDR) scene. It is an ill-posed problem to restore the saturated regions of the LDR image. In this paper, the saturated…

HDR reconstruction is an important task in computer vision with many industrial needs. The traditional approaches merge multiple exposure shots to generate HDRs that correspond to the physical quantity of illuminance of the scene. However,…

Physically-based rendering (PBR) is key for immersive rendering effects used widely in the industry to showcase detailed realistic scenes from computer graphics assets. A well-known caveat is that producing the same is computationally heavy…

Recovering the geometry and materials of objects from a single image is challenging due to its under-constrained nature. In this paper, we present Neural LightRig, a novel framework that boosts intrinsic estimation by leveraging auxiliary…

The increasingly populated cities of the 21st Century face the challenge of being sustainable and resilient spaces for their inhabitants. However, climate change, among other problems, makes these objectives difficult to achieve. The Urban…

Existing image deraining methods typically rely on single-input, single-output, and single-scale architectures, which overlook the joint multi-scale information between external and internal features. Furthermore, single-domain…

Building realistic wide scale outdoor 3D content with sufficient visual quality to observe at walking eye level or from driven vehicles is often carried out by large teams of artists skilled in modelling, texturing, material shading and…

Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and imperfect captures that current Neural Radiance Field (NeRF) pipelines only partly…

Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to computer vision systems by degrading visibility and color fidelity. Consequently, effective shadow removal and ALN are critical for…

We investigate the use of photometric invariance and deep learning to compute intrinsic images (albedo and shading). We propose albedo and shading gradient descriptors which are derived from physics-based models. Using the descriptors,…

Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low…