The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

This paper introduces FutureSurf, a benchmark and dataset for evaluating dynamic-scene reconstruction methods' ability to predict future surface geometry.

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

The paper introduces U4D, an uncertainty-aware framework that synthesizes 4D LiDAR scenes by prioritizing the reconstruction of geometrically difficult and uncertain regions first, leading to state-of…

The paper addresses the challenge of multi-turn view planning for VLMs by proposing an iterative framework that uses self-exploration and view graph distillation, significantly improving planning perf…

This paper proposes a top-down framework for generating hierarchical 3D scene graphs of indoor scenes, including room layout and object layout within each room.

City-Mesh3R is a scalable, end-to-end framework that reconstructs high-fidelity, watertight 3D surface meshes of entire city-scale environments directly from large collections of multi-view images.

T2Mo is a novel framework that generates controllable dynamic 3D object shapes by combining explicit 3D trajectories for spatial guidance with natural language text semantics.

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

GeoSAM-3D proposes a novel framework for open-vocabulary 3D scene segmentation from simple monocular video by propagating object prompts using a geodesic distance kernel on a reconstructed Gaussian sc…

This paper introduces GS-Agent, an end-to-end multi-agent framework that generates realistic, dynamic, and controllable 4D physical worlds from natural language descriptions by emulating human creatio…

The paper proposes a novel method to improve the simultaneous representation of appearance and geometry in 3D Gaussian Splatting by introducing an additional geometry opacity parameter.

The paper introduces an adaptive feature-optimized vision front end that intelligently selects and budgets visual features for 3D reconstruction, significantly improving reconstruction quality and com…

GeM-NR proposes a novel, training-free framework to achieve general multi-view image editing, enabling consistent edits that drastically change both the geometry and appearance of a nonrigid scene.

The paper introduces SPAWN, a training-free method that allows users to inject specified visual concepts into existing autoregressive world models, enabling controllable scene composition beyond the i…

This paper applies the MAP-Elites algorithm to procedurally generate diverse and high-quality First-Person Shooter maps using novel map representations.

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…