相关论文: SceneScribe-1M: A Large-Scale Video Dataset with C…
In recent years, 3D scene graphs have emerged as a powerful world representation, offering both geometric accuracy and semantic richness. Combining 3D scene graphs with large language models enables robots to reason, plan, and navigate in…
We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text-driven methods that often suffer from geometric drift or…
Large-scale video repositories are increasingly available for modern video understanding and generation tasks. However, transforming raw videos into high-quality, task-specific datasets remains costly and inefficient. We present DataCube,…
Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent…
Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D,…
City-scale 3D point cloud is a promising way to express detailed and complicated outdoor structures. It encompasses both the appearance and geometry features of segmented city components, including cars, streets, and buildings, that can be…
Despite substantial progress in video understanding, most existing datasets are limited to Earth's gravitational conditions. However, microgravity alters human motion, interactions, and visual semantics, revealing a critical gap for…
The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality…
While text-to-video diffusion models have advanced significantly, creating coherent long-form content remains unreliable due to stochastic sampling artifacts. This necessitates generating multiple candidates, yet verifying them creates a…
Descriptive video service (DVS) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting…
Recent advances in deep learning have brought significant progress in visual grounding tasks such as language-guided video object segmentation. However, collecting large datasets for these tasks is expensive in terms of annotation time,…
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…
Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On the other hand, learning from unlabeled large-scale collected…
In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image…
We present a unified network for simultaneously generating videos and their corresponding entity segmentation and depth maps from text prompts. We utilize colormap to represent entity masks and depth maps, tightly integrating dense…
Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video…
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited…
We present SpatialMem, a memory-centric system for long-horizon, language-grounded retrieval and QA from egocentric video, where metric 3D serves as an interpretable indexing scaffold rather than an explicit mapping objective. Starting from…
Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support a limited input modalities or rely on implicit generation…
Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must…