CoTL: Compact Token Learning for 3D Scene Representation
cs.CV
Submitted: 2026-10-13
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- C3G: Learning Compact 3D Representations with 2K Gaussians
- SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
- D'ej\`a View: Looping Transformers for Multi-View 3D Reconstruction
- Geometric Context Transformer for Streaming 3D Reconstruction
- NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
- Surflo: Consistent 3D Surface Flow Model with Global State
- ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion
- GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias
- Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
- QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction
- Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding
- Flow Matching for Generative Modeling
- DINOv2: Learning Robust Visual Features without Supervision
- TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
- Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models
- ZipSplat: Fewer Gaussians, Better Splats
- VGGT-$\Omega$
- VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
- TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models