相关论文: LONG3R: Long Sequence Streaming 3D Reconstruction

Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and…

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global…

Online monocular 3D reconstruction enables dense scene recovery from streaming video but remains fundamentally limited by the stability-adaptation dilemma: the reconstruction model must rapidly incorporate novel viewpoints while preserving…

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,…

Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image…

This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D…

3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-scene optimization or fail to provide efficient incremental…

Realtime 4D reconstruction for dynamic scenes remains a crucial challenge for autonomous driving perception. Most existing methods rely on depth estimation through self-supervision or multi-modality sensor fusion. In this paper, we propose…

Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a…

View-conditioned 3D generators such as SAM 3D, TRELLIS and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrives as long monocular streams. Naively applying these…

In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global…

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR…

Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing…

Streaming feed-forward 3D reconstruction enables real-time joint estimation of scene geometry and camera poses from RGB images. However, without explicit dynamic reasoning, streaming models can be affected by moving objects, causing…

Reconstructing surgical scenes from monocular endoscopic video is critical for advancing robotic-assisted surgery. However, the application of state-of-the-art general-purpose reconstruction models is constrained by two key challenges: the…

We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this…

We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an…

Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per…

Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…

Dense 3D reconstruction from continuous image streams requires both accurate geometric aggregation and stable long-term memory management. Recent feed-forward reconstruction frameworks integrate observations through persistent memory…