Related papers: RIC: Rotate-Inpaint-Complete for Generalizable Sce…
We present a new framework to reconstruct holistic 3D indoor scenes including both room background and indoor objects from single-view images. Existing methods can only produce 3D shapes of indoor objects with limited geometry quality…
Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…
Inpainting involves filling in missing pixels or areas in an image, a crucial technique employed in Mixed Reality environments for various applications, particularly in Diminished Reality (DR) where content is removed from a user's visual…
We study the problem of synthesizing immersive 3D indoor scenes from one or more images. Our aim is to generate high-resolution images and videos from novel viewpoints, including viewpoints that extrapolate far beyond the input images while…
3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this…
Inverse rendering aims to decompose a scene into its geometry, material properties and light conditions under a certain rendering model. It has wide applications like view synthesis, relighting, and scene editing. In recent years, inverse…
In this work, we present the recursive camera-painting approach to obtain painterly smudging in real-time rendering applications. We have implemented recursive camera painting as both a GPU-based ray-tracing and in a Virtual Reality game…
Recently, neural implicit surfaces have become popular for multi-view reconstruction. To facilitate practical applications like scene editing and manipulation, some works extend the framework with semantic masks input for the…
High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints - leads to missing information and incomplete surfaces in the…
3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked objects in a scene are replaced with new contents that blend…
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of…
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse convolutional network, CircNet, that jointly models local…
Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous approaches have attempted to overcome the ill-posedness of the task by distilling priors from 2D foundational models and by imposing hand-crafted…
3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks. In contrast to traditional generative learned models which encode the full…
One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with…
We introduce a method for high-quality 3D reconstruction from multi-view images. Our method uses a new point-based representation, the regularized dipole sum, which generalizes the winding number to allow for interpolation of per-point…
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We…
Reconstructing a dynamic scene from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen…
Movie productions use high resolution 3d characters with complex proprietary rigs to create the highest quality images possible for large displays. Unfortunately, these 3d assets are typically not compatible with real-time graphics engines…