ScanNet
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses
arXiv:2605.20823v3 Announce Type: replace Abstract: Open-vocabulary 3D scene graph generation seeks to describe object instances and their relations with flexible natural-language predicates. The central difficulty is not only vocabulary expansion, but supervision reliability: relation annotations in 3D scene graph datasets are selective, and many valid object-pair relations are unannotated. We propose RelWitness, a framework for open-vocabulary 3D scene graph generation from posed RGB-D...
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
arXiv:2604.20395v2 Announce Type: replace Abstract: Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seconds per scene, while pseudo-labeled end-to-end approaches rely on fragmented masks and external region proposals. We present SpaCeFormer, a proposal-free space-curve transformer that runs in 0.12--0.30 seconds per scene...
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
arXiv:2605.30855v1 Announce Type: new Abstract: Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response. However, maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging. Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from \textit{Latent--RGB Cycling}, where generated...
Zero-Shot Polygon Matching with Pre-trained Models for Pose Estimation and Polygon Cloud from Challenging Stereo
Announce Type: replace Abstract: While stereo matching has achieved maturity for 0D point and 1D line primitives, establishing correspondences for 2D polygons remains largely unexplored due to challenges including disparity discontinuity, scale variation, training dependency, and poor generalization, limiting downstream tasks such as pose estimation and 3D reconstruction. To address these issues, we are the first to propose a Zero-shot Polygon Matching paradigm with Pre-trained Models (i.e.,...
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
arXiv:2605.30855v2 Announce Type: replace Abstract: Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response. However, maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging. Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from \textit{Latent--RGB Cycling}, where...
Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models
arXiv:2606.02742v1 Announce Type: new Abstract: Spatial reasoning is fundamental to robotics, autonomy, and embodied AI, yet modern vision-language models (VLMs) remain unreliable on metric distance queries. A common assumption is that consistent predictions across viewpoints reflect geometric grounding.
ZipSplat: Fewer Gaussians, Better Splats
arXiv:2606.05102v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolution rather than scene complexity. A flat wall and a richly textured object thus produce equally many Gaussians despite very different geometric needs. We propose ZipSplat, a token-based feed-forward model that...
$\text{VG}^2$GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
Announce Type: replace Abstract: Gaussian splatting has shown strong potential for 3D reconstruction and novel view synthesis. However, most existing methods require accurate camera parameters and per-scene optimization, while feed-forward methods with pixel-aligned Gaussian primitives often suffer from artifacts and non-uniform primitives. In this paper, we propose $\text{VG}^2$GT, a Voxel-Gaussian Splatting Visual Geometry-Grounded Transformer.
RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruning
arXiv:2606.06255v1 Announce Type: new Abstract: Point clouds are a primary sensory representation for robotic perception, underpinning LiDAR-based autonomous driving, simultaneous localization and mapping (SLAM), and navigation. Within these pipelines, Farthest Point Sampling (FPS) is the most well-known downsampling operator, as its uniform coverage preserves the geometric structure on which downstream perception relies. However, the large time complexity of classical FPS scales poorly with...
Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration
Announce Type: replace Abstract: In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, CLIP's inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their...