Related papers: Level-S$^2$fM: Structure from Motion on Neural Lev…

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…

Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations…

Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limitation of this approach is that multiple SDFs can produce geometries that…

In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in…

Neural implicit functions have achieved impressive results for reconstructing 3D shapes from single images. However, the image features for describing 3D point samplings of implicit functions are less effective when significant variations…

Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a…

Multi-view mesh reconstruction remains a core challenge in computer graphics and vision, especially for recovering high-frequency geometry from sparse observations. Recent methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance…

Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a…

Camera pose estimation is a long-standing computer vision problem that to date often relies on classical methods, such as handcrafted keypoint matching, RANSAC and bundle adjustment. In this paper, we propose to formulate the Structure from…

The raw depth images captured by RGB-D cameras using Time-of-Flight (TOF) or structured light often suffer from incomplete depth values due to weak reflections, boundary shadows, and artifacts, which limit their applications in downstream…

The recovery of 3D shape and pose from 2D landmarks stemming from a large ensemble of images can be viewed as a non-rigid structure from motion (NRSfM) problem. Classical NRSfM approaches, however, are problematic as they rely on heuristic…

We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…

We introduce a method that can learn to predict scene-level implicit functions for 3D reconstruction from posed RGBD data. At test time, our system maps a previously unseen RGB image to a 3D reconstruction of a scene via implicit functions.…

The paper introduces an accurate solution to dense orthographic Non-Rigid Structure from Motion (NRSfM) in scenarios with severe occlusions or, likewise, inaccurate correspondences. We integrate a shape prior term into variational…

We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1.3 seconds on a single A100…

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in…

Recently, methods for neural surface representation and rendering, for example NeuS, have shown that learning neural implicit surfaces through volume rendering is becoming increasingly popular and making good progress. However, these…

In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks…

We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses and for reconstructing accurate poses from noisy or partial…

Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid,…