9 citations · 36 across the 38 of their papers we have counts for
30 papers · 1 filter
VGGT-CAD: Reconstructing Parametric CAD 3D Model with Geometric Grounding
Chunan Yu, Tianrun Chen, Fu Shen +3
Parametric CAD reconstruction requires recovering both precise geometry and editable modeling operations from visual observations, making it challenging under limited and ambiguous…
MoWorld: A Flash World Model
Team Moxin, Deyi Ji, Tianrun Chen +37
The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive per…
Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
An Zhao, Shengyuan Zhang, Zhongjian Sun +5
Flow Matching models have demonstrated strong performance across a wide range of generative tasks. However, their reliance on ODE-based iterative sampling incurs substantial comput…
Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation
Runlong Cao, Ying Zang, Chuanwei Zhou +4
Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and…
4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
Ying Zang, Xuanyi Liu, Yidong Han +9
Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance s…
The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
Jiatong Li, Zheng Chen, Kai Liu +91
This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge…
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Xuanyi Liu, Chunan Yu, Deyi Ji +6
Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing frameworks primarily rely on a ``pure evict…
The Fourth Challenge on Image Super-Resolution (4) at NTIRE 2026: Benchmark Results and Method Overview
Zheng Chen, Kai Liu, Jingkai Wang +150
This paper presents the NTIRE 2026 image super-resolution (4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to r…
Semantic Manipulation Localization
Zhenshan Tan, Chenhan Lu, Yuxiang Huang +6
Image Manipulation Localization (IML) aims to identify edited regions in an image. However, with the increasing use of modern image editing and generative models, many manipulation…
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
Ying Zang, Yidong Han, Chaotao Ding +8
Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences whe…
HD-VGGT: High-Resolution Visual Geometry Transformer
Tianrun Chen, Yuanqi Hu, Yidong Han +11
High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visua…
SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
Chaojun Ni, Cheng Chen, Xiaofeng Wang +12
Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To…
SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
Tianrun Chen, Runlong Cao, Xinda Yu +8
The rapid rise of large-scale foundation models has reshaped the landscape of image segmentation, with models such as Segment Anything achieving unprecedented versatility across di…
Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
Lanyun Zhu, Deyi Ji, Tianrun Chen +2
The success of DeepSeek-R1 demonstrates the immense potential of using reinforcement learning (RL) to enhance LLMs' reasoning capabilities. This paper introduces Retrv-R1, the firs…
From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching
Ying Zang, Yuanqi Hu, Xinyu Chen +7
In the era of immersive consumer electronics, such as AR/VR headsets and smart devices, people increasingly seek ways to express their identity through virtual fashion. However, ex…
CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
Cheng Chen, Jiacheng Wei, Tianrun Chen +8
Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-in…
POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
Lanyun Zhu, Tianrun Chen, Qianxiong Xu +5
Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel…
Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
Ying Zang, Yuncan Gao, Jiangi Zhang +7
This work advances zero-shot interactive segmentation for remote sensing imagery through three key contributions. First, we propose a novel sketch-based prompting method, enabling…
Syllables to Scenes: Literary-Guided Free-Viewpoint 3D Scene Synthesis from Japanese Haiku
Chunan Yu, Yidong Han, Chaotao Ding +6
In the era of the metaverse, where immersive technologies redefine human experiences, translating abstract literary concepts into navigable 3D environments presents a fundamental c…
Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
Ying Zang, Runlong Cao, Jianqi Zhang +8
Sketches, with their expressive potential, allow humans to convey the essence of an object through even a rough contour. For the first time, we harness this expressive potential to…
Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Lanyun Zhu, Tianrun Chen, Deyi Ji +2
This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or…
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion
Shengyuan Zhang, An Zhao, Ling Yang +7
Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the prac…
Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry
Tianrun Chen, Chunan Yu, Yuanqi Hu +8
In this paper, we propose Img2CAD, the first approach to our knowledge that uses 2D image inputs to generate CAD models with editable parameters. Unlike existing AI methods for 3D…
SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More
Tianrun Chen, Ankang Lu, Lanyun Zhu +7
The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable succ…