Related papers: Sparse-View 3D Reconstruction: Recent Advances and…
Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention…
Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with,…
Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing…
City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF,…
We present PreF3R, Pose-Free Feed-forward 3D Reconstruction from an image sequence of variable length. Unlike previous approaches, PreF3R removes the need for camera calibration and reconstructs the 3D Gaussian field within a canonical…
Neural rendering methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have achieved significant progress in photorealistic 3D scene reconstruction and novel view synthesis. However, most existing models assume…
Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point…
3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This…
3D Gaussian Splatting (3DGS) has demonstrated remarkable real-time performance in novel view synthesis, yet its effectiveness relies heavily on dense multi-view inputs with precisely known camera poses, which are rarely available in…
We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for multiview shape reconstruction operate on sparse shape…
3D reassembly is a challenging spatial intelligence task with broad applications across scientific domains. While large-scale synthetic datasets have fueled promising learning-based approaches, their generalizability to different domains is…
Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging depth prior for…
Single-image 3D human reconstruction aims to reconstruct the 3D textured surface of the human body given a single image. While implicit function-based methods recently achieved reasonable reconstruction performance, they still bear…
3D human reconstruction from a single image is a challenging problem and has been exclusively studied in the literature. Recently, some methods have resorted to diffusion models for guidance, optimizing a 3D representation via Score…
Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…
Neural implicit reconstruction via volume rendering has demonstrated its effectiveness in recovering dense 3D surfaces. However, it is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…
Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view…
3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high. Ground-breaking research in the neural radiance field (NeRF) by utilizing Multi-Layer Perceptions…
Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have…