3D Vision

Uni-3DAR: Autoregressive framework unifies 3D generation/understanding, compressing spatial tokens for faster, versatile AI.

Sonata: Reliable 3D point cloud self-supervised learning through self-distillation, achieving SOTA with less data.

NuiScene: Enables efficient & unbounded outdoor scene generation by encoding scene chunks as uniform vector sets and outpainting.

GFS-VL: Enhancing few-shot 3D segmentation by synergizing vision-language models with few-shot learning for robust real-world application.

4DGS-1K: Achieves 1000+ FPS for dynamic scene rendering via a compact, memory-efficient framework, offering a 41x storage reduction and 9x faster speed.

DeepMesh: RL-guided auto-regressive creation of artist-quality 3D meshes, enhanced by tokenization & DPO for human-aligned aesthetics.

Roblox presents Cube, a 3D intelligence model using shape tokenization for text-to-shape, shape-to-text, and text-to-scene generation.

WideRange4D: A new benchmark & reconstruction method for high-quality 4D scenes with wide-range movements, pushing the boundaries of 4D reconstruction.

MM-Spatial enhances multimodal LLMs with 3D spatial reasoning via a novel dataset and benchmark, improving performance on spatial understanding tasks.

Infinite Mobility: Procedural generation of high-fidelity articulated objects for scalable embodied AI training.

VGGT: a fast, end-to-end transformer that infers complete 3D scene attributes from multiple views, outperforming optimization-based methods.

LHM: Animatable 3D avatars from a single image in seconds.

ETCH: Equivariantly fitting bodies to clothed humans through tightness for better pose and shape accuracy.

MaRI: Accurately retrieves textures from images by bridging the gap between visual representations and material properties across diverse domains.

PE3R: Achieves fast and accurate 3D scene reconstruction from 2D images by enhanced perception and efficiency.

Kiss3DGen generates 3D assets by repurposing 2D diffusion models, enabling efficient 3D editing and enhancement.

DIFIX3D+ improves 3D reconstructions by reducing artifacts via single-step diffusion models, enhancing novel-view synthesis quality and consistency.

EDGS: Achieves faster, high-quality dynamic scene rendering by sparse time-variant attribute modeling and intelligent static area filtering.

ArtGS: Achieves state-of-the-art, efficient interactable replicas of complex articulated objects via Gaussian Splatting.

MagicArticulate automates 3D model animation preparation by generating skeletons and skinning weights, overcoming prior manual methods’ limitations, and introducing Articulation-XL, a large-scale benc…