Related papers: MeMix: Writing Less, Remembering More for Streamin…

Recent advances in generalizable 3D Gaussian Splatting (3DGS) have enabled rapid 3D scene reconstruction within seconds, eliminating the need for per-scene optimization. However, existing methods primarily follow an offline reconstruction…

We propose VisFusion, a visibility-aware online 3D scene reconstruction approach from posed monocular videos. In particular, we aim to reconstruct the scene from volumetric features. Unlike previous reconstruction methods which aggregate…

We present a novel framework for mesh reconstruction from unstructured point clouds by taking advantage of the learned visibility of the 3D points in the virtual views and traditional graph-cut based mesh generation. Specifically, we first…

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…

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation -- multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either…

Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows…

Dense reconstructions often contain errors that prior work has so far minimised using high quality sensors and regularising the output. Nevertheless, errors still persist. This paper proposes a machine learning technique to identify errors…

We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks do feature extraction from scratch at each frame in the absence of ad-hoc solutions. We…

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…

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…

Real-time reconstruction of dynamic 3D scenes from uncalibrated video streams demands robust online methods that recover scene dynamics from sparse observations under strict latency and memory constraints. Yet most dynamic reconstruction…

Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…

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…

Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close to this ability. When tasked with learning to classify objects by training on non-repeating video…

In supervised machine learning, an agent is typically trained once and then deployed. While this works well for static settings, robots often operate in changing environments and must quickly learn new things from data streams. In this…

Mesh reconstruction from multi-view images is a fundamental problem in computer vision, but its performance degrades significantly under sparse-view conditions, especially in unseen regions where no ground-truth observations are available.…

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…

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…

Reconstructing a dynamic scene from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen…

Recently, 3D reconstruction and generation have demonstrated impressive novel view synthesis results, achieving high fidelity and efficiency. However, a notable conditioning gap can be observed between these two fields, e.g., scalable 3D…