SuperPrimitive: Scene Reconstruction at a Primitive Level
- URL: http://arxiv.org/abs/2312.05889v2
- Date: Wed, 17 Apr 2024 16:13:22 GMT
- Title: SuperPrimitive: Scene Reconstruction at a Primitive Level
- Authors: Kirill Mazur, Gwangbin Bae, Andrew J. Davison,
- Abstract summary: Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem.
Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues.
We address this issue with a new image representation which we call a SuperPrimitive.
- Score: 23.934492494774116
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues. Such pixel-level approaches suffer from ambiguities or violations of multi-view consistency (e.g. caused by textureless or specular surfaces). We address this issue with a new image representation which we call a SuperPrimitive. SuperPrimitives are obtained by splitting images into semantically correlated local regions and enhancing them with estimated surface normal directions, both of which are predicted by state-of-the-art single image neural networks. This provides a local geometry estimate per SuperPrimitive, while their relative positions are adjusted based on multi-view observations. We demonstrate the versatility of our new representation by addressing three 3D reconstruction tasks: depth completion, few-view structure from motion, and monocular dense visual odometry.
Related papers
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D [79.94479633598102]
Large Spatial Model (LSM) processes unposed RGB images directly into semantic radiance fields.
LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward operation.
It can generate versatile label maps by interacting with language at novel viewpoints.
arXiv Detail & Related papers (2024-10-24T17:54:42Z) - DoubleTake: Geometry Guided Depth Estimation [17.464549832122714]
Estimating depth from a sequence of posed RGB images is a fundamental computer vision task.
We introduce a reconstruction which combines volume features with a hint of the prior geometry, rendered as a depth map from the current camera location.
We demonstrate that our method can run at interactive speeds, state-of-the-art estimates of depth and 3D scene in both offline and incremental evaluation scenarios.
arXiv Detail & Related papers (2024-06-26T14:29:05Z) - RelPose++: Recovering 6D Poses from Sparse-view Observations [66.6922660401558]
We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images)
We build on the recent RelPose framework which learns a network that infers distributions over relative rotations over image pairs.
Our final system results in large improvements in 6D pose prediction over prior art on both seen and unseen object categories.
arXiv Detail & Related papers (2023-05-08T17:59:58Z) - Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images.
This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories.
We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
arXiv Detail & Related papers (2022-08-04T14:13:35Z) - MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface
Reconstruction [72.05649682685197]
State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views.
This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints.
Motivated by recent advances in the area of monocular geometry prediction, we explore the utility these cues provide for improving neural implicit surface reconstruction.
arXiv Detail & Related papers (2022-06-01T17:58:15Z) - GeoFill: Reference-Based Image Inpainting of Scenes with Complex
Geometry [40.68659515139644]
Reference-guided image inpainting restores image pixels by leveraging the content from another reference image.
We leverage a monocular depth estimate and predict relative pose between cameras, then align the reference image to the target by a differentiable 3D reprojection.
Our approach achieves state-of-the-art performance on both RealEstate10K and MannequinChallenge dataset with large baselines, complex geometry and extreme camera motions.
arXiv Detail & Related papers (2022-01-20T12:17:13Z) - Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views.
Our method is supervised and trained on a public dataset of shapes from common object categories.
arXiv Detail & Related papers (2020-08-18T06:33:40Z) - Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [59.906948203578544]
We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object.
We first estimate per-view depth maps using a deep multi-view stereo network.
These depth maps are used to coarsely align the different views.
We propose a novel multi-view reflectance estimation network architecture.
arXiv Detail & Related papers (2020-03-27T21:28:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.