Related papers: MoRe: Motion-aware Feed-forward 4D Reconstruction …
Three-dimensional (3D) ultrasound (US) aims to provide sonographers with the spatial relationships of anatomical structures, playing a crucial role in clinical diagnosis. Recently, deep-learning-based freehand 3D US has made significant…
We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint representation of dense 3D point maps and 3D scene flows in a…
In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric…
Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…
Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. Classical optimization-based…
Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding…
Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted…
Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct supervision on large-scale 3D datasets. In contrast, the limited…
We propose a simple yet effective approach to enhance the performance of feed-forward 3D reconstruction models. Existing methods often struggle near depth discontinuities, where standard regression losses encourage spatial averaging and…
Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for ultra-high-resolution videos prohibitively expensive. To…
Scenes in the real world are often composed of several static and dynamic objects. Capturing their 4-dimensional structures, composition and spatio-temporal configuration in-the-wild, though extremely interesting, is equally hard.…
Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…
We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn…
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.…
We propose EMORe, an adaptive reconstruction method designed to enhance motion robustness in free-running, free-breathing self-gated 5D cardiac magnetic resonance imaging (MRI). Traditional self-gating-based motion binning for 5D MRI often…
4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, computationally expensive, and difficult to scale to longer sequences. We introduce a…
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…
Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating…
We propose MoRe-ERL, a framework that combines Episodic Reinforcement Learning (ERL) and residual learning, which refines preplanned reference trajectories into safe, feasible, and efficient task-specific trajectories. This framework is…