Related papers: MapAnything: Universal Feed-Forward Metric 3D Reco…
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…
Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast to most real-time capable approaches, our approach does not…
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses…
Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range. However, such prior might not be directly available…
We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key…
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…
Volumetric biological imaging often involves compromising high temporal resolution at the expense of high spatial resolution when popular scanning methods are used to capture 3D information. We introduce an integrated experimental and image…
Intermediate feature representations represent the backbone for the expressivity and adaptability of deep neural networks. However, their geometric structure remains poorly understood. In this submission, we provide indirect insights into…
Recovering a 3D surface from its surface normal map, a problem known as normal integration, is a key component for photometric shape reconstruction techniques such as shape-from-shading and photometric stereo. The vast majority of existing…
Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive…
General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this…
In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one…
Depth imaging is vital for many emerging technologies with applications in augmented reality, robotics, gesture detection, and facial recognition. These applications, however, demand compact and low-power systems beyond the capabilities of…
We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, non-rigid motion and the inner human body shape from a single…
Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a…
Performing single image holistic understanding and 3D reconstruction is a central task in computer vision. This paper presents an integrated system that performs dense scene labeling, object detection, instance segmentation, depth…
Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…
We consider the problem of reconstructing a full 360{\deg} photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find this problem to be severely ill-posed. We thus take an…
We introduce a novel camera model for monocular 3D Morphable Model (3DMM) regression methods that effectively captures the perspective distortion effect commonly seen in close-up facial images. Fitting 3D morphable models to video is a key…
Reconstructing simulation-ready deformable objects is important for vision, graphics, and robotics. Existing physics-driven methods can recover physical digital twins from videos, but they suffer from two fundamental limitations: they…