Explanipedia

Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning Open

Ziyu Ma, Chenhui Gou, Yiming Hu, Xiangxiang Chu, Jianfei Cai · 2025

Large Multimodal Models (LMMs) have shown promising in-context learning (ICL) capabilities, but scaling to many-shot settings remains difficult due to limited context length and high inference cost. To address these challenges, task-vector…

Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video Open

Seonghwa Choi, Moonkyeong Choi, Mingyu Jang, Jaekyung Kim, Jianfei Cai , et al. · 2025

Sharpness-Aware Data Generation for Zero-shot Quantization Open

Dung Hoang-Anh, Cuong Phu Le, Jianfei Cai, Thanh-Toan Do · 2025

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…

An Empirical Study on How Video-LLMs Answer Video Questions Open

Chenhui Gou, Z. Ma, Zicheng Duan, Haoyu He, Feng Chen , et al. · 2025

Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However, most existing efforts focus on improving performance, with …

MU-Diff: a mutual learning diffusion model for synthetic MRI with Application for brain lesions Open

Sanuwani Dayarathna, Yicheng Wu, Jianfei Cai, Tien‐Tsin Wong, Meng Law , et al. · 2025

Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes Open

Duy-Tho Le, Trung Pham, Jianfei Cai, Hamid Rezatofighi · 2025

Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings…

VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior Open

Xinyi Yang, Baolu Li, Yiming Zhang, Zhenfei Yin, Lei Bai , et al. · 2025

Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabil…

PCGS: Progressive Compression of 3D Gaussian Splatting Open

Yihang Chen, Meng Yao Li, Qianyi Wu, Weiyao Lin, Mehrtash Harandi , et al. · 2025

3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practical applications. While many compression techniques have bee…

HAC++: Towards 100X Compression of 3D Gaussian Splatting Open

Yihang Chen, Qianyi Wu, Weiyao Lin, Mehrtash Harandi, Jianfei Cai · 2025

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compres…

Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles Open

Chuang Lin, Bingbing Zhuang, Shanlin Sun, Ziyu Jiang, Jianfei Cai , et al. · 2024

The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops …

PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting Open

Cheng Zhang, Haofei Xu, Qianyi Wu, Camilo Cruz Gambardella, Dinh Phung , et al. · 2024

With the advent of portable 360° cameras, panorama has gained significant attention in applications like virtual reality (VR), virtual tours, robotics, and autonomous driving. As a result, wide-baseline panorama view synthesis has emerged …

Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation Open

Minh Tuan Tran, Trung Le, Xuan-May Le, Jianfei Cai, Mehrtash Harandi , et al. · 2024

Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller dataset…

MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views Open

Yuedong Chen, Chuanxia Zheng, Haofei Xu, Bohan Zhuang, Andrea Vedaldi , et al. · 2024

We introduce MVSplat360, a feed-forward approach for 360° novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficie…

Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering Open

Teng Wei, Qianyi Wu, Jianmin Zheng, Hamid Rezatofighi, Jianfei Cai · 2024

Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled high-fideli…

Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis Open

Hongyu Sun, Qiuhong Ke, Yongcai Wang, Wang Chen, Kang Yang , et al. · 2024

This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-effic…

Fast Feedforward 3D Gaussian Splatting Compression Open

Yihang Chen, Qianyi Wu, Meng Yao Li, Weiyao Lin, Mehrtash Harandi , et al. · 2024

With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, pre…

McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction Open

Daxuan Ren, Hezi Shi, Jianmin Zheng, Jianfei Cai · 2024

Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysis Open

Xianbing Zhao, Lizhen Qu, Tao Feng, Jianfei Cai, Buzhou Tang · 2024

This work proposes a novel and simple sequential learning strategy to train models on videos and texts for multimodal sentiment analysis. To estimate sentiment polarities on unseen out-of-distribution data, we introduce a multimodal model …

McCaD: Multi-Contrast MRI Conditioned, Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis Open

Sanuwani Dayarathna, Kh Tohidul Islam, Bohan Zhuang, Guang Yang, Jianfei Cai , et al. · 2024

Magnetic Resonance Imaging (MRI) is instrumental in clinical diagnosis, offering diverse contrasts that provide comprehensive diagnostic information. However, acquiring multiple MRI contrasts is often constrained by high costs, long scanni…

McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction Open

Daxuan Renınst, Hezi Shiınst, Jianmin Zheng, Jianfei Cai · 2024

Iso-surface extraction from an implicit field is a fundamental process in various applications of computer vision and graphics. When dealing with geometric shapes with complicated geometric details, many existing algorithms suffer from hig…

How Well Can Vision Language Models See Image Details? Open

Chenhui Gou, Abdulwahab Felemban, Faizan Farooq Khan, Deyao Zhu, Jianfei Cai , et al. · 2024

Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains unc…

GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI Open

Pengcheng Chen, Ye Jin, Guoan Wang, Yanjun Li, Zhongying Deng , et al. · 2024

Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals, and can be applied in various fields. In the medical field, LVLMs have a high potential to offer substantial …

AFFnet - a deep convolutional neural network for the detection of atypical femur fractures from anteriorposterior radiographs Open

Hanh H. Nguyen, Duy Lê, Catherine Shore‐Lorenti, Colin Chen, Jörg Schilcher , et al. · 2024

Despite well-defined criteria for radiographic diagnosis of atypical femur fractures (AFFs), missed and delayed diagnosis is common. An AFF diagnostic software could provide timely AFF detection to prevent progression of incomplete or deve…

Differentiable Convex Polyhedra Optimization from Multi-view Images Open

Daxuan Ren, Haiyi Mei, Hezi Shi, Jianmin Zheng, Jianfei Cai , et al. · 2024

This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differen…

SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation Open

Guoan Wang, Ye Jin, Junlong Cheng, Tianbin Li, Zhaolin Chen , et al. · 2024

Volumetric medical image segmentation is pivotal in enhancing disease diagnosis, treatment planning, and advancing medical research. While existing volumetric foundation models for medical image segmentation, such as SAM-Med3D and SegVol, …

DrVideo: Document Retrieval Based Long Video Understanding Open

Ziyu Ma, Chenhui Gou, Hengcan Shi, Bin Sun, Shutao Li , et al. · 2024

Most of the existing methods for video understanding primarily focus on videos only lasting tens of seconds, with limited exploration of techniques for handling long videos. The increased number of frames in long videos poses two main chal…

PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction Open

Shangyu Chen, Zizheng Pan, Jianfei Cai, Dinh Phung · 2024

Personalizing a large-scale pretrained Text-to-Image (T2I) diffusion model is challenging as it typically struggles to make an appropriate trade-off between its training data distribution and the target distribution, i.e., learning a novel…

How Far Can We Compress Instant-NGP-Based NeRF? Open

Yihang Chen, Qianyi Wu, Mehrtash Harandi, Jianfei Cai · 2024

In recent years, Neural Radiance Field (NeRF) has demonstrated remarkable capabilities in representing 3D scenes. To expedite the rendering process, learnable explicit representations have been introduced for combination with implicit NeRF…

Evaluation of the effectiveness of ankle arthrodesis options Open

Ran Wang, И. Ф. Ахтямов, Jianfei Cai, Б. Г. Зиатдинов, E. S. Schigaev · 2024

Introduction Treatment methods for late stages of ankle osteoarthritis are varied, but the issue of assessing the long-term results of various fixation methods has not yet been studied, and this issue is of great importance in clinical pra…

Taming Stable Diffusion for Text to 360° Panorama Image Generation Open

Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang, Dinh Phung , et al. · 2024

Generative models, e.g., Stable Diffusion, have enabled the creation of photorealistic images from text prompts. Yet, the generation of 360-degree panorama images from text remains a challenge, particularly due to the dearth of paired text…

Jianfei Cai YOU? Author Swipe