4 citations · 17 across the 25 of their papers we have counts for
27 papers
Let RGB Be the Language of Vision
Timing Yang, Jinrui Yang, Xinlong Li +11
This work introduces a unified formulation for vision models, where diverse forms of visual information beyond natural images, such as masks, depth maps, and other structured visua…
KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis
Vivekjyoti Banerjee, Abhay Yadav, Rama Chellappa +1
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. Howev…
Zero-Shot Personalization of Objects via Textual Inversion
Aniket Roy, Maitreya Suin, Rama Chellappa
Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this pr…
CAM3R: Camera-Agnostic Model for 3D Reconstruction
Namitha Guruprasad, Abhay Yadav, Cheng Peng +1
Recovering dense 3D geometry from unposed images remains a foundational challenge in computer vision. Current state-of-the-art models are predominantly trained on perspective datas…
MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
Deming Li, Kaiwen Jiang, Yutao Tang +3
In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challe…
Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes
Zhao-Yang Wang, Jieneng Chen, Jiang Liu +2
Gait recognition, a fundamental biometric technology, leverages unique walking patterns for individual identification, typically using 2D representations such as silhouettes or ske…
Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis
Zhao-Yang Wang, Zhimin Shao, Anirudh Nanduri +4
Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environments. Current works typically focus on…
EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
Jiahao Wang, Luoxin Ye, TaiMing Lu +8
Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world m…
MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance
Aniket Roy, Maitreya Suin, Ketul Shah +1
Low-Rank Adaptation (LoRA) has gained prominence as a computationally efficient method for fine-tuning generative models, enabling distinct visual concept synthesis with minimal ov…
DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization
Aniket Roy, Shubhankar Borse, Shreya Kadambi +8
We tackle the challenge of jointly personalizing content and style from a few examples. A promising approach is to train separate Low-Rank Adapters (LoRA) and merge them effectivel…
Speedy MASt3R
Jingxing Li, Yongjae Lee, Abhay Kumar Yadav +3
Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization. MASt3R redefines image matching as a 3D task by leve…
GenEx: Generating an Explorable World
Taiming Lu, Tianmin Shu, Junfei Xiao +8
Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step to…
An Immersive Multi-Elevation Multi-Seasonal Dataset for 3D Reconstruction and Visualization
Xijun Liu, Yifan Zhou, Yuxiang Guo +2
Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-…
An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos
Arun Reddy, Ketul Shah, Corban Rivera +3
In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models h…
FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions
Michael Sprintson, Rama Chellappa, Cheng Peng
We introduce FusionRF, a novel framework for digital surface reconstruction from satellite multispectral and panchromatic images. Current work has demonstrated the increased accura…
StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models
Yuxiang Guo, Faizan Siddiqui, Yang Zhao +2
Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown im…
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Zhaoliang Zhang, Tianchen Song, Yongjae Lee +4
Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a…
BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling
Cheng Peng, Yutao Tang, Yifan Zhou +4
Recent efforts in using 3D Gaussians for scene reconstruction and novel view synthesis can achieve impressive results on curated benchmarks; however, images captured in real life a…
MV2MAE: Multi-View Video Masked Autoencoders
Ketul Shah, Robert Crandall, Jie Xu +4
Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this p…
Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Models
Basudha Pal, Arunkumar Kannan, Ram Prabhakar Kathirvel +2
Diffusion models have achieved great progress in face generation. However, these models amplify the bias in the generation process, leading to an imbalance in distribution of sensi…
Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
Shraman Pramanick, Guangxing Han, Rui Hou +6
The ability of large language models (LLMs) to process visual inputs has given rise to general-purpose vision systems, unifying various vision-language (VL) tasks by instruction tu…
Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
Arun Reddy, William Paul, Corban Rivera +3
In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a…
Instruct2Attack: Language-Guided Semantic Adversarial Attacks
Jiang Liu, Chen Wei, Yuxiang Guo +5
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions. We make use o…
DIFFNAT: Improving Diffusion Image Quality Using Natural Image Statistics
Aniket Roy, Maiterya Suin, Anshul Shah +3
Diffusion models have advanced generative AI significantly in terms of editing and creating naturalistic images. However, efficiently improving generated image quality is still of…