Related papers: LONG3R: Long Sequence Streaming 3D Reconstruction

Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…

Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds…

Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive…

We introduce G-CUT3R, a novel feed-forward approach for guided 3D scene reconstruction that enhances the CUT3R model by integrating prior information. Unlike existing feed-forward methods that rely solely on input images, our method…

With the growing demand for live video streaming, there is an increasing need for low-latency and high-quality transmission, especially with the advent of 5G networks. While 5G offers hardware-level improvements, effective software…

Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challenges: (1)…

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…

Reconstruction is a fundamental task in 3D vision and a fundamental capability for spatial intelligence. Particularly, streaming 3D reconstruction is central to real-time spatial perception, yet existing recurrent online models often suffer…

How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time-consuming per-scene optimization, distorted geometry in…

In-place gesture-based virtual locomotion techniques enable users to control their viewpoint and intuitively move in the 3D virtual environment. A key research problem is to accurately and quickly recognize in-place gestures, since they can…

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches…

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…

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 propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear computational complexity, further scaling the model's capability.…

We present Pow3r, a novel large 3D vision regression model that is highly versatile in the input modalities it accepts. Unlike previous feed-forward models that lack any mechanism to exploit known camera or scene priors at test time, Pow3r…

We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global…

Real-time 3D scene reconstruction from RGB-D sensor data, as well as the exploration of such data in VR/AR settings, has seen tremendous progress in recent years. The combination of both these components into telepresence systems, however,…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…