Related papers: Mem4D: Decoupling Static and Dynamic Memory for Dy…
Dynamic and static components in scenes often exhibit distinct properties, yet most 4D reconstruction methods treat them indiscriminately, leading to suboptimal performance in both cases. This work introduces SDD-4DGS, the first framework…
Image-based 3D reconstruction is one of the most important tasks in Computer Vision with many solutions proposed over the last few decades. The objective is to extract metric information i.e. the geometry of scene objects directly from…
Vision-language models (VLMs) have demonstrated strong performance in 2D scene understanding and generation, but extending this unification to the physical world remains an open challenge. Existing 3D and 4D approaches typically embed scene…
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video. Unlike previous methods that estimate single-view depth maps separately on each key-frame and fuse them later, we propose to…
High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios, which enables numerous immersive VR/AR applications. However, recent advances still fail to provide…
Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models…
Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The…
Recent advancements in 2D/3D generative techniques have facilitated the generation of dynamic 3D objects from monocular videos. Previous methods mainly rely on the implicit neural radiance fields (NeRF) or explicit Gaussian Splatting as the…
While the keypoint-based maps created by sparse monocular simultaneous localisation and mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desired for many robotic tasks. Solutions involving depth cameras…
With the rapid development of 3D reconstruction technology, research in 4D reconstruction is also advancing, existing 4D reconstruction methods can generate high-quality 4D scenes. However, due to the challenges in acquiring multi-view…
4D reconstruction of human-object interaction is critical for immersive VR/AR experience and human activity understanding. Recent advances still fail to recover fine geometry and texture results from sparse RGB inputs, especially under…
The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…
Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation,…
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video.…
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second),…
Existing 4D synthesis methods primarily focus on object-level generation or dynamic scene synthesis with limited novel views, restricting their ability to generate multi-view consistent and immersive dynamic 4D scenes. To address these…
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…
We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training…
Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision. Current techniques either require dense correspondences and rely on motion and deformation cues, or assume a highly accurate…
The reconstruction of three-dimensional dynamic scenes is a well-established yet challenging task within the domain of computer vision. In this paper, we propose a novel approach that combines the domains of 3D geometry reconstruction and…