Related papers: Mem3R: Streaming 3D Reconstruction with Hybrid Mem…

The rapid development of Large Multimodal Models (LMMs) has led to remarkable progress in 2D visual understanding; however, extending these capabilities to 3D scene understanding remains a significant challenge. Existing approaches…

Streaming 3D reconstruction demands long-horizon state updates under strict latency constraints, yet stateful recurrent models often suffer from geometric drift as errors accumulate over time. We revisit this problem from a Grassmannian…

A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video…

Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed…

Widespread RGB-Depth (RGB-D) sensors and advanced 3D reconstruction technologies facilitate the capture of indoor spaces, improving the fields of augmented reality (AR), virtual reality (VR), and extended reality (XR). Nevertheless, current…

Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D…

We present Fin3R, a simple, effective, and general fine-tuning method for feed-forward 3D reconstruction models. The family of feed-forward reconstruction model regresses pointmap of all input images to a reference frame coordinate system,…

We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets. DreamCraft3D++ inherits the multi-stage generation process of DreamCraft3D, but replaces the time-consuming…

The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions. The NERF algorithm, suitable for underwater scenes or scattering media, is also evolving.…

Real-time 3D volumetric streaming is a transformative technology that enables the seamless transmission and rendering of high-fidelity 3D models, enhancing applications in virtual reality (VR), augmented reality (AR), gaming, telepresence,…

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and…

This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods.…

Reconstructing the hand mesh from one single RGB image is a challenging task because hands are often occluded by other objects. Most previous works attempt to explore more additional information and adopt attention mechanisms for improving…

Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content…

This paper presents A3D, an adaptive 3D network that can infer at a wide range of computational constraints with one-time training. Instead of training multiple models in a grid-search manner, it generates good configurations by trading off…

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

The application of monocular dense Simultaneous Localization and Mapping (SLAM) is often hindered by high latency, large GPU memory consumption, and reliance on camera calibration. To relax this constraint, we propose EC3R-SLAM, a novel…

Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory…

Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene…

The modern computer graphics pipeline can synthesize images at remarkable visual quality; however, it requires well-defined, high-quality 3D content as input. In this work, we explore the use of imperfect 3D content, for instance, obtained…