Related papers: WinT3R: Window-Based Streaming Reconstruction with…
Multi-view 3D reconstruction has remained an essential yet challenging problem in the field of computer vision. While DUSt3R and its successors have achieved breakthroughs in 3D reconstruction from unposed images, these methods exhibit…
We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene…
Dense 3D reconstruction from RGB images traditionally assumes static camera pose estimates. This assumption has endured, even as recent works have increasingly focused on real-time methods for mobile devices. However, the assumption of a…
We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods requiring per-scene optimization, Edit3r directly predicts…
Recent advances in 2D-to-3D perception have enabled the recovery of 3D scene semantics from unposed images. However, prevailing methods often suffer from limited generalization, reliance on per-scene optimization, and semantic…
High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints - leads to missing information and incomplete surfaces in the…
This work proposes a new method for real-time dense 3d reconstruction for common 360{\deg} action cams, which can be mounted on small scouting UAVs during USAR missions. The proposed method extends a feature based Visual monocular SLAM…
Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…
Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…
We introduce UniCon3R, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffer from artifacts, where bodies float above the ground or…
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many sparse query-based methods have already attempted to improve the…
We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale…
Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available…
Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When…
Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic hand-object reconstruction from RGB sequences involves a…
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…
We present Human3R, a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. Unlike previous approaches that rely on multi-stage pipelines, iterative…
Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the…
Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline is significant, noticeable parallax occurs-meaning the…
The objective of this work is human pose estimation in videos, where multiple frames are available. We investigate a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames…