papers

Publications (13)

cs.CV2026

GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model

Qida Cao, Xinyuan Hu, Changyue Shi +3

This paper describes our method for Track 2 of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge on smoke-degraded images. In this task, smoke reduces image visibil…

cs.CV2023

ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields

Xiang Feng, Yongbo He, Yubo Wang +6

Neural Radiance Fields (NeRF) have achieved great success in the task of synthesizing novel views that preserve the same resolution as the training views. However, it is challengin…

cs.CV2026

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results

Shuhong Liu, Chenyu Bao, Ziteng Cui +103

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to…

cs.CV2026

REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting

Changyue Shi, Minghao Chen, Yiping Mao +4

Bridging the gap between complex human instructions and precise 3D object grounding remains a significant challenge in vision and robotics. Existing 3D segmentation methods often s…

eess.IV2025

LymphAtlas- A Unified Multimodal Lymphoma Imaging Repository Delivering AI-Enhanced Diagnostic Insight

Jiajun Ding, Beiyao Zhu, Xiaosheng Liu +2

This study integrates PET metabolic information with CT anatomical structures to establish a 3D multimodal segmentation dataset for lymphoma based on whole-body FDG PET/CT examinat…

cs.CV2025

SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images

Xinyuan Hu, Changyue Shi, Chuxiao Yang +6

Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, exi…