Related papers: Multi-body Non-rigid Structure-from-Motion

Estimating camera intrinsics and extrinsics is a fundamental problem in computer vision, and while advances in structure-from-motion (SfM) have improved accuracy and robustness, open challenges remain. In this paper, we introduce a robust…

Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, small-scale deformation and offer limited consideration for…

Visual localization is a critical task in mobile robotics, and researchers are continuously developing new approaches to enhance its efficiency. In this article, we propose a novel approach to improve the accuracy of visual localization…

We present a novel framework to reconstruct complete 3D human shapes from a given target image by leveraging monocular unconstrained images. The objective of this work is to reproduce high-quality details in regions of the reconstructed…

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become an increasingly important research focus. Despite their…

Recovering world-coordinate human motion from monocular videos with humanoid robot retargeting is significant for embodied intelligence and robotics. To avoid complex SLAM pipelines or heavy temporal models, we propose a lightweight,…

We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDFs). Compared to other representations, SDFs have the advantage that they can…

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing…

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor…

With their high-fidelity scene representation capability, the attention of SLAM field is deeply attracted by the Neural Radiation Field (NeRF) and 3D Gaussian Splatting (3DGS). Recently, there has been a surge in NeRF-based SLAM, while…

We propose CrossHuman, a novel method that learns cross-guidance from parametric human model and multi-frame RGB images to achieve high-quality 3D human reconstruction. To recover geometry details and texture even in invisible regions, we…

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The…

Our world is full of identical objects (\emphe.g., cans of coke, cars of same model). These duplicates, when seen together, provide additional and strong cues for us to effectively reason about 3D. Inspired by this observation, we introduce…

Structure from Motion or the sparse 3D reconstruction out of individual photos is a long studied topic in computer vision. Yet none of the existing reconstruction pipelines fully addresses a progressive scenario where images are only…

We describe a set of tools for analyzing, visualizing, and assessing architectural/construction progress with unordered photo collections and 3D building models. With our interface, a user guides the registration of the model in one of the…

Estimating the pose of a moving camera from monocular video is a challenging problem, especially due to the presence of moving objects in dynamic environments, where the performance of existing camera pose estimation methods are susceptible…

Much progress has been made in the supervised learning of 3D reconstruction of rigid objects from multi-view images or a video. However, it is more challenging to reconstruct severely deformed objects from a single-view RGB image in an…

This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. Previous approaches treat dynamic…

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…

Structure-from-motion (SfM) largely relies on feature tracking. In image sequences, if disjointed tracks caused by objects moving in and out of the field of view, occasional occlusion, or image noise, are not handled well, corresponding SfM…