AI Model2023
Estimates and tracks 6D poses of novel objects without per-object fine-tuning — supports both model-based (CAD) and model-free (few reference images) setups. Trained on large-scale synthetic data with a transformer-based architecture and contrastive learning; CVPR 2024 highlight with demos and pretrained weights.
AI Dataset2024
Provides point-accurate annotations of interactive parts in high-resolution indoor laser-scan point clouds, plus affordance labels, motion axes and natural-language task descriptions; includes aligned iPad RGB-D video slices with 2D projections for multimodal research.
Embodied AI2026
Reconstructs camera poses and dense 3D point clouds from video streams using a feed‑forward foundation model. Combines a Geometric Context Transformer (anchor + local window + trajectory memory) with paged KV‑cache attention to enable stable, long‑sequence streaming inference (~20 FPS at 518×378).
AI Dataset2026
Large-scale synthetic video dataset of 236,937 1080p clips (≈5,841 hours) of digital humans with per-frame metric depth and camera parameters — built as a controllable supplement for world-model pretraining, camera-motion generalization, and geometry-aware physical-AI research.
AI Dataset2026
Large-scale synthetic video dataset of physically simulated multi-object interaction scenes for training and evaluating models on physical reasoning, depth and optical-flow estimation, instance segmentation, and physics-grounded captioning. Provides RGB + lossless depth, per-frame instance masks, per-object physics annotations (NPZ), VLM-grounded captions, and USD scene files — useful for world-model and simulation-to-real work; commercial use permitted.
AI Dataset2026
Open egocentric multimodal dataset for embodied AI and robot learning captured on commodity iPhone Pro: ~200 hours and ~10M RGB frames with LiDAR depth, ARKit 6‑DoF poses, IMU, two‑hand MANO mocap, room meshes, and hierarchical action captions.
Analyzes spatial representations in vision–language models and reveals a consistent vertical-position ↔ distance entanglement; introduces SpatialTunnel, a synthetic benchmark that exposes this perspective-driven shortcut, and provides code and a project page.
AI Video Papers2026
Stores a persistent 3D scene cache directly in a diffusion model's latent space to produce temporally and spatially consistent videos. Constructs memory via depth-guided back-projection and queries it with direct latent-space warping — achieving large speed and memory gains versus pixel-space 3D baselines.
Synthesizes scalable, photoreal 3D Earth tiles from georeferenced satellite imagery using a generative 3D Gaussian Splatting representation; trained on urban reconstructions, it generates novel scenes at under 10 minutes/km² with hierarchical LOD for real-time web map visualization and Embodied AI use cases.
Provides a dual-path approach for spatial vision-language models: a Language-Only Reasoning (LOR) path for stepwise linguistic deduction and a Detect-Then-Reason (DTR) path that detects 3D cues via region tokens before numerical inference. Trains with chain-of-thought cold-start supervision and reinforcement learning to improve 3D grounding and multi-step spatial reasoning.
AI Dataset2026
Zeren Jiang, Yushi Lan +9Visual Geometry Group, University of Oxford, Nanyang Technological University +1
Provides multiview synthetic RGB video clips with per-frame depth, instance masks, dense long-range 3D point tracks, camera poses, and SMPL‑X human pose/shape labels for 4D reconstruction, tracking, and geometry-aware novel-view synthesis. Includes ~4.7K clips (1.4M frames) and is licensed for AI training.
AI Dataset2026
Provides ~50M multimodal annotations organized for unified training across structured visual understanding, segmentation, dense geometric prediction, and multi-view reconstruction — released as task-specific JSONL files that reference original image assets rather than redistributing raw images.