PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 16334-16343
Abstract
No abstract availableFunding Information
- PCL-CMCC Foundation for Science and Innovation (SQ2510230001)
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM413)
- Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology (2024B1212010006)
- Shenzhen Science and Technology Program (SYSPG20241211173440004)
- R24115SG MIGU-PKU META VISION TECHNOLOGY INNOVATION LAB (None)
- Outstanding Talents Training Fund in Shenzhen (None)
This publication has 17 references indexed in Scilit:
- Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise2025
- MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision2025
- Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors2025
- T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy2024
- DUSt3R: Geometric 3D Vision Made Easy2024
- I'M HOI: Inertia-Aware Monocular Capture of 3D Human-Object Interactions2024
- BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion2023
- ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild2022
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset2020
- A Naturalistic Open Source Movie for Optical Flow Evaluation2012