Related papers: LRM: Large Reconstruction Model for Single Image t…

Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations…

Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally requires prior knowledge of camera poses for the training…

Object-centric reconstruction seeks to recover the 3D structure of a scene through composition of independent objects. While this independence can simplify modeling, it discards strong signals that could improve reconstruction, notably…

Image restoration aims to reconstruct the latent clear images from their degraded versions. Despite the notable achievement, existing methods predominantly focus on handling specific degradation types and thus require specialized models,…

3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during…

We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our procedural 3D dataset, Zeroverse, which is automatically…

Accurately predicting the 3D shape of any arbitrary object in any pose from a single image is a key goal of computer vision research. This is challenging as it requires a model to learn a representation that can infer both the visible and…

Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware…

Online reconstructing and rendering of large-scale indoor scenes is a long-standing challenge. SLAM-based methods can reconstruct 3D scene geometry progressively in real time but can not render photorealistic results. While NeRF-based…

We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. A single forward pass of an encoder network…

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…

The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive…

Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images. However, NeRFs have limited generalization properties, which means that we need to use significant…

Reconstructing dynamic assets from video data is central to many in computer vision and graphics tasks. Existing 4D reconstruction approaches are limited by category-specific models or slow optimization-based methods. Inspired by the recent…

For collecting high-quality high-resolution (HR) MR image, we propose a novel image reconstruction network named IREM, which is trained on multiple low-resolution (LR) MR images and achieve an arbitrary up-sampling rate for HR image…

Recent medical image reconstruction techniques focus on generating high-quality medical images suitable for clinical use at the lowest possible cost and with the fewest possible adverse effects on patients. Recent works have shown…

We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details. Unlike previous large reconstruction models that prepare images under fixed and simple lighting…

We present the Locally Adaptive Morphable Model (LAMM), a highly flexible Auto-Encoder (AE) framework for learning to generate and manipulate 3D meshes. We train our architecture following a simple self-supervised training scheme in which…

We propose the NeRF-LEBM, a likelihood-based top-down 3D-aware 2D image generative model that incorporates 3D representation via Neural Radiance Fields (NeRF) and 2D imaging process via differentiable volume rendering. The model represents…

Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling. However, we observe that IRNs with deeper networks are difficult to train, thus hindering…