paper-with-me

3D Geometry Prediction

2개 벤치마크 · 논문 9편 · 이 태스크의 논문 보기 →

Benchmarks

Molecule3D test

결과 4개

Molecule3D val

결과 4개

Most implemented

Papers

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models

2026-05-27 · Haozhan Shen, Tiancheng Zhao, Kangjia Zhao, Jianwei Yin arxiv

Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schemes are now widely used as foundation bac…

3D Geometry PredictionVideo Generation

2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

2026-03-20 · Tianbao Zhang, Zhenyu Liang, Zhenbo Song, Nana Wang 외 arxiv

High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models are fundamentally limited by their scalability to real-world, high-resolut…

3D Geometry PredictionAutonomous Driving

Dens3R: A Foundation Model for 3D Geometry Prediction

2025-07-22 · Xianze Fang, Jingnan Gao, Zhe Wang, Zhuo Chen 외 arxiv

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometr…

3D Geometry Prediction3D Reconstruction

GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details

2024-05-20 · Boqian Li, Xuan Li, Ying Jiang, Tianyi Xie 외

Traditional 3D garment creation is labor-intensive, involving sketching, modeling, UV mapping, and texturing, which are time-consuming and costly. Recent advances in diffusion-based generative models have enabled new pos…

3D Generation3D Geometry Prediction3DGSGarment Reconstruction+2

Point Cloud Diffusion Models for Automatic Implant Generation

2023-03-14 · Paul Friedrich, Julia Wolleb, Florentin Bieder, Florian M. Thieringer 외

Advances in 3D printing of biocompatible materials make patient-specific implants increasingly popular. The design of these implants is, however, still a tedious and largely manual process. Existing approaches to automat…

3D Geometry PredictionPoint Cloud Completion

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

2022-09-08 · ChemRxiv 2022 9 · Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng 외

Molecular representation learning (MRL) has gained tremendous attention due to its critical role in learning from limited supervised data for applications like drug design. In most MRL methods, molecules are treated as 1…

3D geometry3D Geometry PredictionDrug DesignMolecular Property Prediction+5

전체 9편 보기 →