Related papers: MV-DUSt3R+: Single-Stage Scene Reconstruction from…
Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate…
DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor…
Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing…
Current multi-view 3D reconstruction methods rely on accurate camera calibration and pose estimation, requiring complex and time-intensive pre-processing that hinders their practical deployment. To address this challenge, we introduce…
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…
Novel view synthesis in 360$^\circ$ scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view…
Room layout estimation from multiple-perspective images is poorly investigated due to the complexities that emerge from multi-view geometry, which requires muti-step solutions such as camera intrinsic and extrinsic estimation, image…
Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS…
Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…
Recovering the 3D geometry of a scene from a sparse set of uncalibrated images is a long-standing problem in computer vision. While recent learning-based approaches such as DUSt3R and MASt3R have demonstrated impressive results by directly…
Recovering 3D information from scenes via multi-view stereo reconstruction (MVS) and novel view synthesis (NVS) is inherently challenging, particularly in scenarios involving sparse-view setups. The advent of 3D Gaussian Splatting (3DGS)…
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…
3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense captures are needed to match the high-quality expectations…
Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…
We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian…
Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…
Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D…
We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with…
In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without…
We present a real-time visual-inertial dense mapping method capable of performing incremental 3D mesh reconstruction with high quality using only sequential monocular images and inertial measurement unit (IMU) readings. 6-DoF camera poses…