Related papers: 360$^\circ$ Reconstruction From a Single Image Usi…

Wide-baseline panorama reconstruction has emerged as a highly effective and pivotal approach for not only achieving geometric reconstruction of the surrounding 3D environment, but also generating highly realistic and immersive novel views.…

3D reconstruction from multiple views is a successful computer vision field with multiple deployments in applications. State of the art is based on traditional RGB frames that enable optimization of photo-consistency cross views. In this…

While recent deep neural networks have achieved promising results for 3D reconstruction from a single-view image, these rely on the availability of RGB textures in images and extra information as supervision. In this work, we propose novel…

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined…

Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction. Existing works either address one part of this problem or focus on independent objects. In this paper, we bridge the gap between…

360{\deg} images and videos have become an economic and popular way to provide VR experiences using real-world content. However, the manipulation of the stereo panoramic content remains less explored. In this paper, we focus on the…

We present a method to learn single-view reconstruction of the 3D shape, pose, and texture of objects from categorized natural images in a self-supervised manner. Since this is a severely ill-posed problem, carefully designing a training…

We present PHORHUM, a novel, end-to-end trainable, deep neural network methodology for photorealistic 3D human reconstruction given just a monocular RGB image. Our pixel-aligned method estimates detailed 3D geometry and, for the first time,…

Differentiable rendering is a very successful technique that applies to a Single-View 3D Reconstruction. Current renderers use losses based on pixels between a rendered image of some 3D reconstructed object and ground-truth images from…

We present Pow3r, a novel large 3D vision regression model that is highly versatile in the input modalities it accepts. Unlike previous feed-forward models that lack any mechanism to exploit known camera or scene priors at test time, Pow3r…

We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries. This is a challenging problem…

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…

Dense matching methods like DUSt3R regress pairwise pointmaps for 3D reconstruction. However, the reliance on pairwise prediction and the limited generalization capability inherently restrict the global geometric consistency. In this work,…

Generic 3D reconstruction from a single image is a difficult problem. A lot of data loss occurs in the projection. A domain based approach to reconstruction where we solve a smaller set of problems for a particular use case lead to greater…

Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas…

In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work…

3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of…

Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are built upon multi-view geometry. State-of-the-art (SOTA)…

We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We recover a 3D shape from a 2D image by first regressing the 2D positions corresponding…

The default strategy for training single-view Large Reconstruction Models (LRMs) follows the fully supervised route using large-scale datasets of synthetic 3D assets or multi-view captures. Although these resources simplify the training…