Hugging Face Trending Papers
RDT-3D: Resolution-Decoupled Training for High-Fidelity 3D Geometry Generation
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
1d ago
RDT-3D: Resolution-Decoupled Training for High-Fidelity 3D Geometry Generation
arXiv:2611.06141v1 Announce Type: new Abstract: High-fidelity 3D geometry generation requires maintaining global structural coherence alongside fine-grained surface details. While recent coarse-to-fi...
arXiv Computer Vision
4d ago
VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation
VoxLution is a coarse‑to‑fine transformer‑based method for generating high‑fidelity 3D indoor scenes. It first creates a low‑resolution spatial layout and then progressively refines the geometry in local chunks using a sequence‑modeling approach over multi‑resolution sparse voxel grids. The method introduces a resolution‑invariant tokenization scheme that encodes octants into a single decimal number and incorporates adjacent chunk boundaries to maintain coherence, achieving state‑of‑the‑art performance on 3D‑FRONT and ScanNet++ benchmarks.
arXiv AI
Oct 9
HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution
Hi3D 3.0, also called Twinkle3D, is an image‑to‑3D generation system that produces watertight triangle meshes at a resolution of 2048³. It improves on previous methods by maintaining high representational precision while fixing surface quality and non‑watertight issues, scaling diffusion generation to 300K geometric tokens, strengthening global shape and local detail in a single stage, and adding a fine‑grained image‑3D cross‑modal interaction to better recover object‑specific structures such as inscriptions. The system outperforms four commercial competitors, recovering 82.1 % of inscribed characters with 98.2 % precision versus 21.7 % recall for the best rival.
arXiv Computer Vision
Sep 22
ScaleBlind: Point Cloud Completion under Unknown Scale
arXiv:2609.23404v1 Announce Type: new Abstract: Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks suc...
arXiv AI
Oct 19
Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
The paper introduces SAGE, a framework that adapts 3D geometric foundation models using weak supervision from raw Internet videos. SAGE employs a hierarchical mining pipeline to generate informative training trajectories, sparse geometric anchoring via SfM point clouds, and dense differentiable consistency through 3D Gaussian rendering, while also replaying a small amount of supervised data to avoid catastrophic forgetting. Experiments on two different backbones show that SAGE reduces Chamfer Distance on unseen benchmarks by 20–42% and consistently improves performance, demonstrating that Internet video can serve as a scalable source for geometric learning.
arXiv Machine Learning
Jun 25
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
arXiv:2312. 00206v4 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis.