3D Vision

Generate wide-scope 3D scenes from single images in a snap!

Create realistic 3D heads with specific hairstyles from text, no 3D hair data needed!

Leveraging video models, researchers achieve state-of-the-art 3D super-resolution by generating ‘video-like’ sequences from unordered images, eliminating artifacts and computational demands.

MOVIS enhances 3D scene generation by improving cross-view consistency in multi-object novel view synthesis.

IDArb: A diffusion model for decomposing images into intrinsic components like albedo, normal, and material properties, handling varying views and lighting.

Training-free method adds physical properties to 3D models using vision-language models.

Neural LightRig uses multi-light diffusion to accurately estimate object normals and materials from a single image, outperforming existing methods.

FreeSplatter: a novel feed-forward framework reconstructs high-quality 3D scenes from uncalibrated sparse-view images, estimating camera poses in seconds.

MIDI: a novel multi-instance diffusion model generates compositional 3D scenes from single images by simultaneously creating multiple 3D instances with accurate spatial relationships and high generali…

ScoreLiDAR: Distilling diffusion models for 5x faster, higher-quality 3D LiDAR scene completion!

2DGS-Room: Seed-guided 2D Gaussian splatting with geometric constraints achieves state-of-the-art high-fidelity indoor scene reconstruction.

Unified 3D latent representation (SLAT) enables versatile high-quality 3D asset generation, significantly outperforming existing methods.

One-shot image to realistic, animatable talking avatar! Novel pipeline uses diffusion models and a hybrid 3DGS-mesh representation, achieving seamless generalization and precise control.

AlphaTablets: A novel 3D plane representation enabling accurate, consistent, and flexible 3D planar reconstruction from monocular videos, achieving state-of-the-art results.

Make-It-Animatable: Instantly create animation-ready 3D characters, regardless of pose or shape, using a novel data-driven framework.

CAT4D: Create realistic 4D scenes from single-view videos using a novel multi-view video diffusion model.

MARVEL-40M+ & MARVEL-FX3D: 40M+ high-quality 3D annotations & a fast two-stage text-to-3D pipeline enabling high-fidelity 3D model generation within 15 seconds.

SplatFlow: A novel multi-view rectified flow model enabling direct 3D Gaussian splatting generation & training-free editing for diverse 3D tasks.

SAR3D: Blazing-fast autoregressive 3D object generation and understanding using a multi-scale VQVAE, achieving sub-second generation and detailed multimodal comprehension.

Self-supervised learning of 3D representations from procedurally generated synthetic shapes achieves comparable performance to models trained on real-world datasets, highlighting the potential of synt…