Related papers: PanoVGGT: Feed-Forward 3D Reconstruction from Pano…
Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, while diffusion-based repair is typically restricted to…
Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…
Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…
We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but…
3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or…
Panoramic semantic segmentation models are typically trained under a strict gravity-aligned assumption. However, real-world captures often deviate from this canonical orientation due to unconstrained camera motions, such as the rotational…
In the field of novel-view synthesis, the necessity of knowing camera poses (e.g., via Structure from Motion) before rendering has been a common practice. However, the consistent acquisition of accurate camera poses remains elusive, and…
3D reconstruction plays an increasingly important role in modern photogrammetric systems. Conventional satellite or aerial-based remote sensing (RS) platforms can provide the necessary data sources for the 3D reconstruction of large-scale…
Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods. In this…
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…
3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent on accurate camera poses typically obtained from computationally intensive processes like…
Recent approaches for predicting layouts from 360 panoramas produce excellent results. These approaches build on a common framework consisting of three steps: a pre-processing step based on edge-based alignment, prediction of layout…
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…
Learning depth from spherical panoramas is becoming a popular research topic because a panorama has a full field-of-view of the environment and provides a relatively complete description of a scene. However, applying well-studied CNNs for…
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional…
The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction without per-scene optimization. However, its billion-parameter scale creates high memory and compute demands, hindering on-device deployment.…
360{\deg} videos have emerged as a promising medium to represent our dynamic visual world. Compared to the "tunnel vision" of standard cameras, their borderless field of view offers a more complete perspective of our surroundings. While…
Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs. However, synthesizing novel views from these panoramic images in real time remains a significant…
Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…
We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models…