Related papers: sshELF: Single-Shot Hierarchical Extrapolation of …

Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details.…

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small…

We aim to tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM). The sparse-view setting is ill-posed and underconstrained, especially for scenes where the camera rotates 360 degrees around a…

We present a method for Sparse view reconstruction with surface element splatting that runs within 3 minutes on a consumer grade GPU. While few methods address sparse radiance field learning from noisy or unposed sparse cameras, shape…

Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or…

Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of…

Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain centered on Gaussian primitives and expose surfaces only…

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based…

Recently, a surge of 3D style transfer methods has been proposed that leverage the scene reconstruction power of a pre-trained neural radiance field (NeRF). To successfully stylize a scene this way, one must first reconstruct a…

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that…

Existing Human NeRF methods for reconstructing 3D humans typically rely on multiple 2D images from multi-view cameras or monocular videos captured from fixed camera views. However, in real-world scenarios, human images are often captured…

In this paper, we aim ambitiously for a realistic yet challenging problem, namely, how to reconstruct high-quality 3D scenes from sparse low-resolution views that simultaneously suffer from deficient perspectives and clarity. Whereas…

We introduce Spurfies, a novel method for sparse-view surface reconstruction that disentangles appearance and geometry information to utilize local geometry priors trained on synthetic data. Recent research heavily focuses on 3D…

We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed scenes using a novel representation VoxSplat, which is a set…

Dynamic urban environments are often captured by cameras placed at spatially separated locations with little or no view overlap. However, most existing 4D reconstruction methods assume densely overlapping views. When applied to such sparse…

We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. This task becomes more difficult when only sparse images are provided as input, a scenario where existing neural…

Surface reconstruction from sparse views aims to reconstruct a 3D shape or scene from few RGB images. The latest methods are either generalization-based or overfitting-based. However, the generalization-based methods do not generalize well…

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…

Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have…

Humans demonstrate remarkable skill in transferring manipulation abilities across objects of varying shapes, poses, and appearances, a capability rooted in their understanding of semantic correspondences between different instances. To…