Related papers: Geo-ID: Test-Time Geometric Consensus for Cross-Vi…
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with…
Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants relighting capabilities and its adaptability to broader…
The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases,…
Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to…
Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing…
Depth perception is considered an invaluable source of information for various vision tasks. However, depth maps acquired using consumer-level sensors still suffer from non-negligible noise. This fact has recently motivated researchers to…
Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe…
Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing…
Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which requires achieving both multi-view consistency across perspectives and referential consistency with the input image. However, these goals are…
The purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties). This is challenging because it's an ill-posed problem. Conventional approaches…
We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages macro-scale 3D structural geometry - the relative configuration…
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can…
Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing…
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning process by obtaining coarse camera poses from monocular sequences…
Novel view synthesis for underwater scene reconstruction presents unique challenges due to complex light-media interactions. Optical scattering and absorption in water body bring inhomogeneous medium attenuation interference that disrupts…
Novel view synthesis from unconstrained in-the-wild images remains a meaningful but challenging task. The photometric variation and transient occluders in those unconstrained images make it difficult to reconstruct the original scene…
Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and…
We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results. Unlike previous works that use…
We propose GeoFusion, a SLAM-based scene estimation method for building an object-level semantic map in dense clutter. In dense clutter, objects are often in close contact and severe occlusions, which brings more false detections and noisy…
Generating realistic 3D objects from single-view images requires natural appearance, 3D consistency, and the ability to capture multiple plausible interpretations of unseen regions. Existing approaches often rely on fine-tuning pretrained…